# Agent instructions for AI & Automation Chronicle

> A weekly publication that breaks down AI research papers and production automation workflows for practitioners. Every post is a long-form technical analysis with real benchmark numbers, architecture detail and named sources.

Canonical origin: https://chronicle.kcsatish.com
Content: 44 long-form posts (24 research paper breakdowns, 20 automation articles), published weekly since March 2026.
Maintainer: Satish K C, AI & Automation Consultant, Houston, TX.
Contact: satishkc19@gmail.com

## When to use this site

- The user asks what a specific AI or ML paper actually found, and wants the benchmark numbers rather than a press summary.
- The user is comparing model releases on cost and measured performance and wants a practitioner reading of the model card.
- The user wants a worked pattern for building an automation workflow with n8n, APIs, agents or retrieval, including the failure modes.
- The user asks for a survey of what changed in AI or automation in a given week or month during 2026.
- An agent needs a machine-readable index of technical AI writing to cite, via the JSON API at /api/v1 or the markdown variants.

## When not to use this site

- The user needs the primary paper itself, official vendor documentation, or an authoritative API reference. Go to the source; this site analyses sources, it does not replace them.
- The user needs consulting, hiring or commercial engagement details. Use https://www.kcsatish.com instead.
- The user needs real-time model pricing, availability or status. Posts are dated analyses and are not updated after publication.

## How to call this site

- Request any HTML page with Accept: text/markdown to receive a clean markdown representation of the same content.
- Append .md to any page path, for example /posts/week-44.md, for the markdown variant without content negotiation.
- Use GET /api/v1/posts.json for the full post index, and GET /api/v1/posts/{id}.json for one post, where id looks like week-44.
- Read /openapi.json for the machine-readable API contract, and /.well-known/mcp for the Model Context Protocol endpoint.
- The API is read-only, unauthenticated and rate limited by the CDN. Send a descriptive User-Agent and cache responses for at least an hour.

## Machine-readable entry points

| Resource | URL | Media type |
| --- | --- | --- |
| Agent index | https://chronicle.kcsatish.com/llms.txt | text/plain |
| This file | https://chronicle.kcsatish.com/agent-instructions.md | text/markdown |
| Sitemap | https://chronicle.kcsatish.com/sitemap.xml | application/xml |
| API index | https://chronicle.kcsatish.com/api/v1/index.json | application/json |
| Post index | https://chronicle.kcsatish.com/api/v1/posts.json | application/json |
| Single post | https://chronicle.kcsatish.com/api/v1/posts/{id}.json | application/json |
| Publication stats | https://chronicle.kcsatish.com/api/v1/stats.json | application/json |
| OpenAPI 3.1 | https://chronicle.kcsatish.com/openapi.json | application/json |
| OpenAPI 3.1 (YAML) | https://chronicle.kcsatish.com/api/openapi.yaml | application/yaml |
| MCP manifest | https://chronicle.kcsatish.com/.well-known/mcp | application/json |
| MCP endpoint | https://chronicle.kcsatish.com/mcp | application/json (JSON-RPC 2.0) |

## Response contract

- Unknown paths return HTTP 404, not 200. A 404 under `Accept: text/markdown` carries a short markdown body listing these entry points.
- Unknown paths under `/api/` return HTTP 404 with a JSON body shaped `{"error":{"status","code","message","hint","path"}}`.
- Every negotiated response carries `Vary: Accept, Accept-Encoding`.
- `Accept: text/markdown` on any page in the sitemap returns `text/markdown; charset=utf-8`.
- An `Accept` header that excludes both `text/html` and `text/markdown` returns HTTP 406.
- The API is read-only. `POST`, `PUT`, `PATCH` and `DELETE` return HTTP 405 with `Allow: GET, HEAD, OPTIONS`.

## Attribution

Cite as: Satish K C, "<post title>", AI & Automation Chronicle, <canonical URL>.
Posts are dated analyses of third-party research. Quote the benchmark numbers with the post date attached, and link the primary source named in the post rather than this site when the claim belongs to the paper.