Essays, claim ledgers, weekly calls and laws, plus AI model release dates, prices and free plans.
Scored across 6 tools
Each tool targets a distinct resource or operation: essays, claim ledgers, weekly calls, AI model records, cross-archive search, and passage-to-archive similarity. The one place overlap could occur (search vs. related_to) is explicitly separated: search ranks query matches across kinds, while related_to takes a passage and returns vocabulary-overlap shares with possible_repeat. The search description even directs agents to the right get_* tool for full reads, which is a clean list/detail split rather than ambiguity.
Four of six tools follow a clear get_<resource> snake_case pattern (get_essay, get_claim_ledger, get_weekly_calls, get_ai_models), and search is a conventional bare-verb exception. related_to breaks the verb_noun convention with a prepositional phrase naming an operation rather than a resource, a minor deviation in an otherwise consistent scheme.
Six tools is well within the well-scoped range and each maps to a genuine content type in the archive (essays, claims, calls, models) plus the two retrieval modes an agent actually needs (search, similarity). No tool looks redundant or padded for the surface described.
The archive's named content types are mostly covered by dedicated retrieval (essays, claims, calls, models), and search spans every kind including laws and free tools. The gap is that laws and free tools have no first-class get_* tool, so they can only be reached through search snippets and a URL — a workaround exists, but the lifecycle is asymmetric.
Get The Durability Curve's record of AI model releases from ten labs (OpenAI, Anthropic, Google, DeepSeek, Meta, xAI, Mistral, Alibaba, Moonshot, Zhipu): when each model came out, with the lab's own announcement as source; for models with a page, the API list prices read at the lab's pricing page on a stated day; for the frontier launches the Access Gap tracks, when ordinary people could first use it, in the app, on the cheapest paid plan and on the free plan, each with its source; and each lab's flagship price and free-plan answer. Search by model or lab name, or filter by lab, release date, frontier status or free-plan access. The record runs to data_through; a newer release is not in it yet. These tools retrieve The Durability Curve's public material. They do not certify that any claim is true.
| Name | Required | Description | Default |
|---|---|---|---|
| lab | No | Only this lab, by name or short name: OpenAI, Anthropic, Google, DeepSeek, Meta, xAI, Mistral, Alibaba, Moonshot or Zhipu. | |
| limit | No | How many models to return, 1 to 50. Default 10. | |
| query | No | A model or lab name in plain words, e.g. "Claude Opus 5.5", "GPT-6.1", "Gemini Flash" or "DeepSeek". Leave empty to list newest first. | |
| on_free_plan | No | true: only models whose lab's free consumer plan includes them; false: only models the free plan is recorded as not including. A model whose free-plan access is unknown, unnamed or restricted is on neither list. Applies to the frontier launches the Access Gap tracks. | |
| frontier_only | No | true: only the frontier releases the /chart/ page plots (models anyone could use on the date given). | |
| released_after | No | YYYY-MM-DD. Only models released after this day. | |
| released_before | No | YYYY-MM-DD. Only models released before this day. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover safety and idempotency, and the description adds non-obvious traits: every fact carries a source, the dataset has a hard recency boundary, and the tools "do not certify that any claim is true." That trust/coverage framing is real value beyond the annotations; it stops short of describing result shape or how limit interacts with the total record.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The first sentence is a single ~110-word run-on with deeply nested clauses enumerating data columns, which hurts scannability despite being front-loaded with the core purpose. Nearly all content is relevant, but it would read far better as a short purpose line followed by bulleted data scope and caveats.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description does the work of explaining what comes back — release date plus source, prices read on a stated day, tiered access availability, flagship/free-plan answers — and covers the freshness boundary. What is missing is shape-level detail (single list vs. grouped per lab, how limit caps results), which for a 7-optional-param read tool is a minor gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% and the parameter descriptions are unusually thorough (e.g. on_free_plan's unknown/unnamed/restricted edge case). The description restates the filter set at a high level but adds no syntax or semantics the schema does not already carry, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource — The Durability Curve's record of AI model releases from ten named labs — and enumerates the exact facts returned (release dates, API list prices with read dates, Access Gap availability, flagship price and free-plan answer). Against siblings like get_claim_ledger, get_essay and get_weekly_calls the resource is unmistakable, so an agent can select it without opening the schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
"Search by model or lab name, or filter by lab, release date, frontier status or free-plan access" gives concrete calling patterns that map onto the query/lab/date/frontier_only/on_free_plan parameters. The freshness caveat ("runs to data_through; a newer release is not in it yet") is a useful when-not signal, but no sibling alternative or exclusion is named.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the claim ledger for one essay: each load-bearing claim it makes, the source it was checked against, the quoted words, where in the source they appear, the date the source was read, and a status saying how the claim was checked. The response defines every status. Filter by claim ids or status, or ask for compact rows. Claims removed during checking are listed separately under "struck", with the reason; they are not claims the essay makes. Only some essays have a ledger: search results and get_essay link to one when it exists. These tools retrieve The Durability Curve's public material. They do not certify that any claim is true.
| Name | Required | Description | Default |
|---|---|---|---|
| ids | No | Only these claim IDs, e.g. ["SL1", "SL6"]. | |
| slug | Yes | The essay's site or Substack slug (case-insensitive), or its full durabilitycurve.com/blog/ or harryfloyd.substack.com/p/ URL. | |
| status | No | Only claims with this status, by its key or label (e.g. "VERIFIED" or "Verified"); the response lists every status. | |
| compact | No | true: each claim as id, status, claim, source, source_url, locator and date_read only (no quoted words or essay sentence). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: the response defines every status, struck claims are returned separately with reasons and are not claims the essay makes, and the tool does not certify truth — real epistemic caveats beyond the structured fields.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
It is front-loaded with what the tool returns and the field list before moving to filtering and caveats, so an agent can act on the first sentence. The final two sentences about retrieval and truth-certification are slightly editorial but still earn their place as scope warnings.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description carries the return-shape burden and does so well, describing the per-claim fields, the separate 'struck' collection, and that statuses are self-documenting. It stops short of saying what actually happens for an essay with no ledger (error versus empty result), which is the remaining gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with per-parameter descriptions for ids, slug, status, and compact, so the schema does the heavy lifting and the baseline is 3. The description's 'Filter by claim ids or status, or ask for compact rows' restates what the schema already documents without adding syntax or edge-case detail.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Get the claim ledger for one essay') and then enumerates exactly what a ledger row contains: claim, source, quoted words, locator, date read, status. It also separates itself from siblings by pointing to search results and get_essay as the way to discover whether a ledger exists.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives a clear availability condition ('Only some essays have a ledger: search results and get_essay link to one when it exists'), which tells the agent how to reach this tool and when it will be useful. It lacks an explicit when-not-to-use statement or a direct contrast with get_essay's own content, which keeps it short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get one Durability Curve essay: by default its full public text as markdown, with its title, dates, canonical field, access, length, sections, tools and a link to its claim ledger when it has one. A long essay can be read in parts: part "outline" lists the sections with their opening lines, part "section" returns one, and part "meta" returns everything but the text. For a part-paid essay only the free part is public, and the text says where it stops. The canonical field is the address to cite. These tools retrieve The Durability Curve's public material. They do not certify that any claim is true.
| Name | Required | Description | Default |
|---|---|---|---|
| part | No | full (default): the whole public text. meta: dates, length, access, sections, tools and a content hash, without the text. outline: each section's heading, length and opening lines. section: one section's text (name it with section). | full |
| slug | Yes | The essay's site or Substack slug (case-insensitive), or its full durabilitycurve.com/blog/ or harryfloyd.substack.com/p/ URL. | |
| section | No | With part "section": the section's number from the outline (0 is the opening, before the first heading) or words from its heading. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the safety hints (readOnly/idempotent), the description provides critical operational behavior, such as the limitation on paywalled content (only the free part is public) and a mandatory disclaimer that the tool does not certify facts.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very dense and lengthy, but every sentence serves a distinct function (content list, part function, paywall constraint, disclaimer). The high information density makes the length well-justified.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity—retrieving various parts of content under specific external constraints (paywalls)—the description is exceptionally complete, leaving no major ambiguity for the AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
While the schema is complete (100% coverage), the description adds vital semantic context: it clarifies that 'slug' can be a full URL or a short identifier, and it explains the exact contents of the enum values for 'part'.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the resource it handles (Durability Curve essays) and details exactly what information is returned (title, dates, canonical field, sections), clearly defining its scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It provides explicit instructions on choosing the `part` parameter (e.g., use 'outline' for sections, 'meta' for data without text) and manages user expectations regarding paywalled content.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the calls printed in The Durability Curve Weekly: dated, checkable predictions, each with the confidence printed at the time and the date or event it resolves on. Filter by status, ID, issue, resolution date or printed confidence. The wording is exactly as printed and never changes after publication. outcome is null until a call resolves. counts describe the calls returned; record describes every call. These tools retrieve The Durability Curve's public material. They do not certify that any claim is true.
| Name | Required | Description | Default |
|---|---|---|---|
| id | No | One call by its ID, e.g. "W02-5". | |
| issue | No | Only the calls printed in this issue of the Weekly. | |
| status | No | open, resolved or all (default). | all |
| resolves_after | No | YYYY-MM-DD. Only calls whose latest resolution date is after this day, earliest first. | |
| resolves_before | No | YYYY-MM-DD. Only calls whose latest resolution date is before this day, earliest first. A call that resolves on an event "or" a date counts by that date. | |
| confidence_at_most | No | Only calls printed at this confidence or lower, in percent, e.g. 30. | |
| confidence_at_least | No | Only calls printed at this confidence or higher, in percent, e.g. 60. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish read-only, idempotent, closed-world behaviour, so the bar is lower, and the description still adds real substance: the printed wording never changes after publication, outcome is null until a call resolves, and counts versus record describe different result scopes. The closing disclaimer that the tools do not certify any claim is true is a meaningful trust caveat not derivable from annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with the resource and its defining traits, then filters, then result-shape notes. It is slightly padded by the two-sentence disclaimer tail, but every sentence carries information rather than filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description accepts the burden of explaining returns and does so adequately: outcome nullity before resolution, and the counts-versus-record distinction, plus the immutability of printed wording. Only the absence of any guidance on result volume or default ordering against siblings keeps it short of full coverage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so every one of the seven parameters is already documented with examples and formats, and the description largely enumerates the same filter set. The one piece of added meaning – that a call resolving on an event 'or' a date is counted by the date – is mirrored in the schema for resolves_before, so the description adds little beyond structured fields.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource – calls printed in The Durability Curve Weekly – and adds their defining nature (dated, checkable predictions with confidence at time of printing). That is far more than a restatement of the name. It does not, however, contrast itself with the closest sibling, get_claim_ledger, which an agent could plausibly confuse with this.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It lists what can be filtered on (status, ID, issue, resolution date, printed confidence), which implies when to reach for this tool, but gives no explicit when-not conditions and no pointer to an alternative among get_claim_ledger, get_essay, related_to or search.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search or list the public archive of The Durability Curve: essays on which kinds of work keep their value as AI gets cheaper, the checked claims in each essay's claim ledger, the dated calls printed in The Durability Curve Weekly, the five laws and two derived principles the essays are tested against, the free tools, and AI model releases. With a query, returns ranked matches, each with its kind (essay, claim, call, law, tool or model), a snippet and a URL (canonical for essay citations); "title_matched" says whether any essay title contains every word of the query, and "none_found" is true when nothing matches enough of the query (the nearest misses are then under "closest", not "results"). With an empty query, lists newest first, filtered by kind, series, has_ledger or access, and "total" counts every match. Read a match in full with get_essay, get_claim_ledger, get_weekly_calls or get_ai_models. These tools retrieve The Durability Curve's public material. They do not certify that any claim is true.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | Only this kind of result: essay, claim, call, law (the framework's laws and principles), tool (the free tools) or model (AI model releases). A list (empty query) defaults to essays. | |
| sort | No | relevance (default for a query) or newest. A list is always newest first. | |
| limit | No | How many results to return, 1 to 25. Default 5. | |
| query | No | What to look for, in plain words, e.g. "agent reliability", "memory chip deposits", a call ID like "W02-5" or a model name like "Claude Opus 5.5". Leave empty to LIST instead (newest first), with the filters below. | |
| access | No | Only essays a reader of durabilitycurve.com gets in full ("free") or only in part ("part paid": the rest is for paid subscribers). | |
| series | No | Only essays (and their claims) in this series, e.g. "The Blueprint". Case does not matter. | |
| has_ledger | No | true: only essays that have a claim ledger. false: only essays without one. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-open-world and non-destructive, so the safety profile is covered. The description adds meaningful behavior beyond that: the ranked-match response shape, 'title_matched', the 'none_found'/'closest' fallback, and the explicit caveat that retrieved material is not certified true.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Purpose and mode distinction are front-loaded and each clause carries information (response fields, fallback behavior, sibling routing, trust caveat). The downside is that it reads as one dense run-on paragraph, which makes it harder to scan than a segmented version would be.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 7 parameters, no output schema and no nested objects, the description covers what an agent needs: both call modes, what each result contains, how near-misses surface, and where to go for full content. Nothing material is left for the agent to guess.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3, but the description adds cross-cutting meaning the schema alone doesn't: a list defaults to essays, sort is relevance for a query but always newest for a list, and query accepts call IDs and model names. These are useful behavioral notes rather than restatements.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource ('Search or list the public archive of The Durability Curve') and enumerates the content types it spans (essays, claim ledgers, weekly calls, laws, tools, models). It also distinguishes itself from the get_* siblings by routing to them for full reads.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It states the two modes clearly: with a query you get ranked matches, with an empty query you get a newest-first list filtered by kind/series/has_ledger/access. It names get_essay, get_claim_ledger, get_weekly_calls and get_ai_models as the way to read a match in full. It does not address when to use this over the related_to sibling.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_ai_modelsget_claim_ledger3 fields changedInput schema / properties / compactAdded value: +{
+ "default": false,
+ "description": "true: each claim as id, status, claim, source, source_url, locator and date_read only (no quoted words or essay sentence).",
+ "type": "boolean"
+}Input schema / properties / idsAdded value: +{
+ "description": "Only these claim IDs, e.g. [\"SL1\", \"SL6\"].",
+ "items": {
+ "maxLength": 20,
+ "type": "string"
+ },
+ "maxItems": 100,
+ "type": "array"
+}Input schema / properties / statusAdded value: +{
+ "description": "Only claims with this status, by its key or label (e.g. \"VERIFIED\" or \"Verified\"); the response lists every status.",
+ "maxLength": 40,
+ "type": "string"
+}get_essay2 fields changedInput schema / properties / partAdded value: +{
+ "default": "full",
+ "description": "full (default): the whole public text. meta: dates, length, access, sections, tools and a content hash, without the text. outline: each section's heading, length and opening lines. section: one section's text (name it with section).",
+ "enum": [
+ "full",
+ "meta",
+ "outline",
+ "section"
+ ],
+ "type": "string"
+}Input schema / properties / sectionAdded value: +{
+ "description": "With part \"section\": the section's number from the outline (0 is the opening, before the first heading) or words from its heading.",
+ "maxLength": 200,
+ "type": "string"
+}get_weekly_calls7 fields changedInput schema / properties / confidence_at_leastAdded value: +{
+ "description": "Only calls printed at this confidence or higher, in percent, e.g. 60.",
+ "maximum": 100,
+ "minimum": 0,
+ "type": "integer"
+}Input schema / properties / confidence_at_mostAdded value: +{
+ "description": "Only calls printed at this confidence or lower, in percent, e.g. 30.",
+ "maximum": 100,
+ "minimum": 0,
+ "type": "integer"
+}Input schema / properties / idAdded value: +{
+ "description": "One call by its ID, e.g. \"W02-5\".",
+ "maxLength": 12,
+ "type": "string"
+}Input schema / properties / issueAdded value: +{
+ "description": "Only the calls printed in this issue of the Weekly.",
+ "maximum": 999,
+ "minimum": 1,
+ "type": "integer"
+}Input schema / properties / resolves_afterAdded value: +{
+ "description": "YYYY-MM-DD. Only calls whose latest resolution date is after this day, earliest first.",
+ "maxLength": 20,
+ "type": "string"
+}Input schema / properties / resolves_before / maxLengthAdded value: +20Input schema / properties / resolves_before / patternRemoved value: -"^\\d{4}-\\d{2}-\\d{2}$"related_tosearch4 fields changedInput schema / properties / accessAdded value: +{
+ "description": "Only essays a reader of durabilitycurve.com gets in full (\"free\") or only in part (\"part paid\": the rest is for paid subscribers).",
+ "enum": [
+ "free",
+ "part paid"
+ ],
+ "type": "string"
+}Input schema / properties / kind / descriptionPrevious value: -"Only this kind of result: essay, claim, call, law (the framework's laws and principles) or tool (the free tools). A list (empty query) defaults to essays."New value: +"Only this kind of result: essay, claim, call, law (the framework's laws and principles), tool (the free tools) or model (AI model releases). A list (empty query) defaults to essays."Input schema / properties / kind / enumPrevious value: -[
- "essay",
- "claim",
- "call",
- "law",
- "tool"
-]New value: +[
+ "essay",
+ "claim",
+ "call",
+ "law",
+ "tool",
+ "model"
+]Input schema / properties / query / descriptionPrevious value: -"What to look for, in plain words, e.g. \"agent reliability\", \"memory chip deposits\" or a call ID like \"W02-5\". Leave empty to LIST instead (newest first), with the filters below."New value: +"What to look for, in plain words, e.g. \"agent reliability\", \"memory chip deposits\", a call ID like \"W02-5\" or a model name like \"Claude Opus 5.5\". Leave empty to LIST instead (newest first), with the filters below."get_claim_ledger1 field changedInput schema / properties / slug / descriptionPrevious value: -"The essay's slug, as in durabilitycurve.com/claims/<slug>/. Get it from search."New value: +"The essay's site or Substack slug (case-insensitive), or its full durabilitycurve.com/blog/ or harryfloyd.substack.com/p/ URL."get_essay1 field changedInput schema / properties / slug / descriptionPrevious value: -"The essay's slug: the last part of its address, as in durabilitycurve.com/blog/<slug>/. Lowercase letters, digits and hyphens. Get it from search."New value: +"The essay's site or Substack slug (case-insensitive), or its full durabilitycurve.com/blog/ or harryfloyd.substack.com/p/ URL."search2 fields changedInput schema / properties / kind / descriptionPrevious value: -"Only this kind of result. A list (empty query) defaults to essays."New value: +"Only this kind of result: essay, claim, call, law (the framework's laws and principles) or tool (the free tools). A list (empty query) defaults to essays."Input schema / properties / kind / enumPrevious value: -[
- "essay",
- "claim",
- "call"
-]New value: +[
+ "essay",
+ "claim",
+ "call",
+ "law",
+ "tool"
+]get_claim_ledgerget_essayget_weekly_callssearchAccess 30+ AI agent essays, CLAUDE.md generator, and readiness assessments.
8 graded AGI-2027 predictions, the 0-100 Thesis Tracker, and a public market-call ledger. Free.
Free fact-checks, papers, source vetting, plus verified AI pricing, comparisons, guides, and tools.
Search, read & publish paid essays. Pay-per-read in USDC on Base (x402); wallet-only, no account.
Add one secure layer between your agents and this server.