# Deepsky

> Aviation Information Management powered by AI. Deepsky builds AI-M systems that unify NOTAMs, manuals, charts, procedures, and operational data into one intelligent platform for airlines and aviation organisations. Flagship product: **The Compliance Department** — automatic compliance you don't have to hire (maps audit standards + your exposition → an audit-ready compliant exposition).

**Constraints and prerequisites (read first):** The public search API (`POST /api/v1/search`) requires **no API key and no sign-up**. Parameter `matchCount` is **1–20** (default 8). Authenticated app routes (logbook, compliance, and other features under the logged-in app) require a **Supabase user session**; protected endpoints are described in the OpenAPI schema and expect `Authorization: Bearer` as documented. Use **`https://www.deepskyai.com`** as the canonical API and site base. The hosted API and website are subject to **normal rate limits and fair-use** behaviour; on **HTTP 429** or **5xx**, use **exponential backoff** and avoid tight loops.

**AI-readable documentation:** This site serves **Markdown** for agents. Append **`.md`** to a path to get an HTML-free document (e.g. `https://www.deepskyai.com/index.md`, `https://www.deepskyai.com/whoweare.md`, `https://www.deepskyai.com/products.md`, and per-article `https://www.deepskyai.com/insights/<slug>.md`). Alternatively, request the same URL as the human page with header **`Accept: text/markdown`**. In-page **hash** links (such as `/#whoweare`) are browser-only and are **not** separate resources; use the **`.md`** routes above for agent consumption.

## Open API — No Authentication Required

Search aviation regulations, manuals, and publications. Open for any agent or application — no API key, no signup.

```
POST https://www.deepskyai.com/api/v1/search
Content-Type: application/json

{"query": "your natural language question", "matchCount": 8}
```

- `query` (string, required): natural language search query
- `matchCount` (integer, optional): number of results, 1–20, default 8
- Returns: `{ query, count, source, matches: [{ content, heading_path, metadata, score }] }`
- Coverage: ICAO, FAA (14 CFR), EASA, CASA regulations and aviation manuals
- OpenAPI schema: https://www.deepskyai.com/.well-known/openapi.json
- Plugin manifest: https://www.deepskyai.com/.well-known/ai-plugin.json

## Open API — No Authentication Required

Search aviation regulations, manuals, and publications. Open for any agent or application — no API key, no signup.

```
POST https://www.deepskyai.com/api/v1/search
Content-Type: application/json

{"query": "your natural language question", "matchCount": 8}
```

- `query` (string, required): natural language search query
- `matchCount` (integer, optional): number of results, 1–20, default 8
- Returns: `{ query, count, source, matches: [{ content, heading_path, metadata, score }] }`
- Coverage: ICAO, FAA (14 CFR), EASA, CASA regulations and aviation manuals
- OpenAPI schema: https://www.deepskyai.com/.well-known/openapi.json
- Plugin manifest: https://www.deepskyai.com/.well-known/ai-plugin.json

## About

- [Homepage](https://deepskyai.com): Deepsky corporate website with product information, team, and contact details
- [About Deepsky](https://deepskyai.com/#whoweare): Founded by Samuel Chandra (A320 Captain & software engineer), Deepsky pioneered AI-M — going beyond traditional Aeronautical Information Management to cover all aviation operational data
- [Products](https://deepskyai.com/#products): The Compliance Department, NOTAM Filtering, Knowledge Assistant, Consulting, and AI Systems Evaluations

## Products

- [The Compliance Department](https://deepskyai.com/#products): Flagship. Automatic compliance you don't have to hire. Inputs: audit standards/regulations (ICAO, FAA, EASA, CASA, ISO 27001, SOC 2, etc.) + your exposition (operations manual, SOPs, policies). Output: a compliant exposition that maps every requirement to the procedure or evidence that satisfies it — auditable, traceable, regulator-ready
- [NOTAM Filtering](https://deepskyai.com/#products): Rules-driven NOTAM processing that turns a manual, variable briefing process into a highly reliable, auditable system — same rules, every briefing
- [Knowledge Assistant](https://deepskyai.com/#products): Precision retrieval system for aviation documents — ask a question and get answers backed by your manuals, regulations, and publications
- [Consulting](https://deepskyai.com/#products): Bespoke consulting to transform variable manual processes into risk-assessed, auditable, systematised processes
- [AI Evaluations](https://deepskyai.com/#products): Independent evaluation and safety/reliability documentation for AI systems in aviation, satisfying regulators and safety committees

## Demos

- [NOTAM Filtering Demo](https://deepskyai.com/demos/notam-filtering): Interactive demonstration of AI-powered NOTAM filtering
- [Manual Explorer Demo](https://deepskyai.com/demos/manual-explorer): Try the Knowledge Assistant's aviation document search

## Insights — AI in Aviation

Expert articles and Q&A derived from the Deepsky podcast series, featuring conversations with leaders in aviation AI.

- [AI in Aviation Primer](https://deepskyai.com/insights/01-primer-ai-aviation): An introduction to how AI is being applied across the aviation industry — from predictive maintenance to autonomous flight
- [Computer Vision for Drone Safety — James Howard, Iris Automation](https://deepskyai.com/insights/02-james-howard-iris-automation): How Iris Automation uses computer vision to build detect-and-avoid systems for drones and works with the FAA to operationalise deep neural networks
- [Ethics of AI in Aviation — Bryant Walker Smith](https://deepskyai.com/insights/03-ethics-ai-aviation-bryant-walker-smith): Ethical considerations in introducing automated vehicles and AI systems to aviation — covering power centralisation, trust, law, and safety-critical systems
- [Fully Autonomous Aircraft — Luuk Van Dijk, Daedalean AI](https://deepskyai.com/insights/04-autonomous-aircraft-luuk-van-dijk-daedalean): How Daedalean AI is building autopilots for fully autonomous flight using computer vision, with EASA collaboration on neural network certification
- [AI-Powered Flight Instruction — Mikhail Klassen, Paladin AI](https://deepskyai.com/insights/05-mikhail-klassen-ai-flight-instruction): How Paladin AI uses machine learning for adaptive pilot training, reducing time and cost while improving training effectiveness
- [Voice AI for Aviation Safety — Conor McKenna, Vocavio](https://deepskyai.com/insights/06-conor-mckenna-vocavio): Prosodic analysis and tonal recognition technology for monitoring flight crew performance in safety-critical environments
- [Ethical AI Frameworks — Lee Glazier, Rolls-Royce](https://deepskyai.com/insights/07-lee-glazier-rolls-royce-ethical-ai): The Aletheia Framework — a 32-step process for ensuring AI systems are accurate, well-managed, and have a positive societal impact
- [Pilot Job Displacement and Autonomous Aircraft — Nick Copland](https://deepskyai.com/insights/08-nick-copland-losing-flying-job): The human impact of automation on pilots and the emotional journey of job loss in aviation
- [Contrails, Climate Change and AI — Adam Durant, SATAVIA](https://deepskyai.com/insights/09-adam-durant-satavia-contrails): How AI-powered atmospheric modelling can reroute aircraft to prevent contrail formation, eliminating two-thirds of aviation's climate warming effect

## Newsletter — AI in Aviation

Weekly insights from Deepsky's Substack on AI and aviation — industry updates, deployment news, and practical guidance.

- [Newsletter Archive](https://deepskyai.com/newsletter): All newsletter entries with links to read on Substack
- [Subscribe on Substack](https://deepsky294.substack.com/subscribe): Subscribe to receive new posts

## AI Agent Resources

- [Home (Markdown, no site chrome)](https://www.deepskyai.com/index.md): Same homepage content as a clean Markdown file for agents
- [Who we are (Markdown)](https://www.deepskyai.com/whoweare.md): Replaces the `/#whoweare` in-page section for tool consumption
- [Products summary (Markdown)](https://www.deepskyai.com/products.md): Replaces the `/#products` in-page section for tool consumption
- [Full Documentation for LLMs](https://deepskyai.com/llms-full.txt): Comprehensive documentation about Deepsky in LLM-optimised format
- [Agent Skills](https://deepskyai.com/#agent-skills): Downloadable AI agent skill packages for aviation professionals

## Optional

Secondary material when you have spare context — skip if you are token-limited.

- [Long-form LLM documentation](https://deepskyai.com/llms-full.txt): Same site in extended form; use when you need more narrative than this `llms.txt`
- [Email newsletter (Substack)](https://deepsky294.substack.com/subscribe): Optional subscription beyond the on-site [newsletter archive](https://deepskyai.com/newsletter)
- [Deepsky podcast (Spotify)](https://open.spotify.com/show/4mr2CCHnsv43YgxWQnFcDk) and [Apple Podcasts](https://podcasts.apple.com/us/podcast/deepsky/id1549828389): Audio interviews; on-site write-ups are under **Insights** above

## API for Agents

- [API Discovery Root](https://www.deepskyai.com/api): Compatibility discovery endpoint for generic agents
- [Canonical API Root (v1)](https://www.deepskyai.com/api/v1): Versioned API index with endpoint map
- [Search Endpoint (Public)](https://www.deepskyai.com/api/search): Public document search alias (`POST`)
- [Search Endpoint (Canonical)](https://www.deepskyai.com/api/v1/search): Canonical versioned search route (`POST`)
- [Skills Registry API](https://www.deepskyai.com/api/skills): Skills registry alias (`GET`)
- [Skills Registry API (v1)](https://www.deepskyai.com/api/v1/skills): Canonical versioned skills route (`GET`)
- [OpenAPI (Dynamic)](https://www.deepskyai.com/api/v1/openapi.json): Machine-readable API schema
- [OpenAPI (Well-Known)](https://www.deepskyai.com/.well-known/openapi.json): Well-known API schema location
- [Agent Plugin Manifest](https://www.deepskyai.com/.well-known/ai-plugin.json): Plugin-style machine manifest
- [API Catalog](https://www.deepskyai.com/.well-known/api-catalog): Machine-readable API catalog

## Contact

- [Email](mailto:admin@deepskyai.com): admin@deepskyai.com
- [LinkedIn](https://www.linkedin.com/company/deepsky-ai): Deepsky company page
- [Podcast on Spotify](https://open.spotify.com/show/4mr2CCHnsv43YgxWQnFcDk): The Deepsky Podcast — exploring how aviation leaders use AI to solve real operational problems
- [Podcast on Apple](https://podcasts.apple.com/us/podcast/deepsky/id1549828389): Also available on Apple Podcasts