# PlatformPilot

> Make your company computable.

PlatformPilot makes your company computable by mapping real-world business assets, relationships, and operations into a structured digital model. That model connects knowledge scattered across your tools and your team's context. On top of it sits a self-improving agent runtime that answers when you ask, investigates when your tools fire, and consolidates while you're away, coming back with what changed. You codify how your team actually works, and we provide the building blocks. We do not claim to know your domain better than you do. It all runs inside your own cloud, so your knowledge and its data never leave your control.

PlatformPilot is a computable environment for your company, built by DynG AI. No schema to design. No taxonomy to build. No consultancy fees. The operational ontology assembles itself from your operations. Every conclusion carries its sources, and every action stays within the limits your team sets.

## When to use PlatformPilot

Reach for PlatformPilot when a task needs a specific company's own accumulated context rather than general knowledge. Best-fit jobs:

- **Recall how this company handled something before**: past incidents, refund decisions, pricing exceptions, customer escalations, engineering postmortems. Call `recall_context` first (or `search_memories` with namespace `episodes`); it usually returns enough context to skip a round of discovery.
- **Find the reusable pattern or policy**: "how do we onboard an enterprise customer", "what is our discount policy", distilled from many episodes. Call `search_memories` with namespace `knowledge`.
- **Record what you just learned** so the next agent or human does not rediscover it: write an episode (what happened, how it resolved) or a reusable pattern with `manage_memories`, then report how the recalled memories worked with `feedback_memories`. One idea per record, name the system explicitly, capture the lesson rather than the log.
- **Investigate a question that spans tools**: Slack, Notion, Drive, GitHub, Linear, Stripe, cloud logs, and 200+ other integrations, with a cited trail for every claim.
- **Run recurring operational work**: scheduled digests, ticket triage, report generation, executed on the company's playbook with the precedent shown.
- **Give any agent persistent, shared memory** through MCP without building a vector store, a schema, or a taxonomy first.

Not a fit: generic web search, one-off summarization of a document with no company context, or anything that must not be shared with the rest of the organization. Everything written to the knowledge layer is visible to every agent and person in that organization.

## How agents call PlatformPilot

- **MCP (preferred)**: `https://mcp.platformpilot.ai/brain/mcp`, Streamable HTTP transport, OAuth 2.1 with PKCE and dynamic client registration. Tools: `recall_context`, `search_memories`, `fetch_memories`, `manage_memories`, `feedback_memories`. Protected resource metadata: https://mcp.platformpilot.ai/.well-known/oauth-protected-resource/brain/mcp
- **Hands-off setup**: paste https://platformpilot.ai/agent-setup/prompt.md into Claude Code, Cursor, Codex, Windsurf, OpenCode, GitHub Copilot, or Claude Desktop and the agent registers the server itself.
- **REST**: https://api.platformpilot.ai with OpenAPI 3.1 at https://api.platformpilot.ai/openapi.json and an interactive reference at https://api.platformpilot.ai/docs. Authenticate with an OAuth 2.0 bearer token from https://auth.platformpilot.ai/ (audience https://api.platformpilot.ai) or an API key from the dashboard.
- **Account**: a PlatformPilot organization is required. Sign-up is self-serve at https://platformpilot.ai/get-started; the dashboard is https://dash.platformpilot.ai.
- **Reading this site**: every page serves Markdown with `Accept: text/markdown` or by appending `.md` to the path (for example https://platformpilot.ai/developers.md). Unknown paths return a real 404 with a Markdown site map.

## How It Works

1. **Connect**: Plug in your tools, webhooks, and cloud environments. That's the whole setup: it starts learning from the first event.
2. **It works your day**: Ask anything and get answers with their sources attached. When an alert, a deal change, or an order problem fires from any of 200+ sources, the investigation starts before you've seen the notification, and every action shows its precedent.
3. **It works your night**: Off-hours, it tidies what it learned: duplicates merge, contradictions surface, and new playbooks are drafted from what worked, then tested against your own history. Morning brings the digest, and the questions it couldn't answer alone.

## One System

What happened, what's true, what to do, and what's earned stay connected in one operational rail:

1. **Every event, captured**: webhooks, chats, and investigations from connected tools land in one timeline of what occurred.
2. **Facts with sources**: events distill into facts, entities, and relationships that retain their source and when they held.
3. **Conclusions that cite**: decisions are scored against your rubric, record their evidence, and flag themselves when that evidence changes.
4. **Work within limits**: actions follow your playbooks inside an autonomy band earned from outcomes people approved.

## Core Capabilities

- **Hidden capabilities, surfaced**: Knowledge scattered across every tool, team, and conversation gets connected, and patterns invisible inside any one silo come into view. What takes shape is an ontology of your operations, not an index of your documents. Search tools remember what your company wrote. This remembers what it did, and how it went.
- **Connect your company's tools safely**: 200+ integrations out of the box including Slack, Notion, Drive, GitHub, Linear, and Stripe. Wired up in minutes, not quarters.
- **Always-on, always streaming**: One live feed of everything happening across your stack.
- **Action, not chat**: Triage tickets, draft replies, run reports. Every action follows your company's playbook, not pretrained defaults, and arrives with its precedent attached. The blast radius stays yours to set.
- **It doesn't wait to be asked**: A webhook fires at 3am. The investigation runs on its own: precedent checked, root cause filed. You wake up to a conclusion, not a notification. And the recurring work you name once ("weekly revenue digest, Mondays 9am") shows up on time, every time.
- **Knowledge, via MCP**: PlatformPilot speaks MCP both ways. Plug it into agents such as Claude Desktop, Claude Code, and OpenAI Agents. No SDK, no client library, ready in seconds. Each agent retrieves context when it calls PlatformPilot, under the same permissions as every other connected agent. Hands-off setup: paste https://platformpilot.ai/agent-setup/prompt.md into your AI coding agent.
- **Enterprise-grade controls**: Granular permissions, full audit trails, org isolation. Your company's knowledge stays inside your company.

## Use Cases

The same building blocks adapt to different domains without shipping a fixed vertical or pretending to know a customer's domain better than they do.

- **Revenue operations**: connect account and deal signals, surface stale evidence, score decisions against the team's rubric, and draft work from approved playbooks.
- **Claims operations**: connect policy and claim signals, apply consistent triage criteria, surface possible recovery paths, and hold work outside the earned autonomy band for review.

These are illustrative workflows. The customer defines the data, rubric, playbooks, approval thresholds, and actions for its own environment.

## Pricing

- **Starter** ($100/mo): Start your knowledge layer
- **Professional** ($200/mo): Put your knowledge to work
- **Team** (Contact us/mo): Your team's shared knowledge
- **Organization** (Contact us/mo): Enterprise-grade platform

Plans and checkout: https://platformpilot.ai/#explore-plans

## Developer resources

- [Developer portal](https://platformpilot.ai/developers): API, MCP server, OAuth 2.0, rate limits, versioning and deprecation policy.
- [Agents API OpenAPI spec](https://api.platformpilot.ai/openapi.json): OpenAPI 3.1, 412 operations with operationIds and descriptions.
- [Agents API reference](https://api.platformpilot.ai/docs): Interactive reference.
- [Web API OpenAPI spec](https://platformpilot.ai/openapi.json): Public endpoints on platformpilot.ai: blog feed, search, status, discovery files.
- [PlatformPilot MCP server](https://mcp.platformpilot.ai/brain/mcp): Streamable HTTP. Requires a PlatformPilot account.
- [MCP gateway](https://mcp.platformpilot.ai/): Index of every hosted MCP server, with its own llms.txt (https://mcp.platformpilot.ai/llms.txt), auth.md on how an agent obtains credentials (https://mcp.platformpilot.ai/auth.md), an ARD catalog (https://mcp.platformpilot.ai/.well-known/ai-catalog.json), and a server card per server.
- [OAuth 2.0 authorization server metadata](https://platformpilot.ai/.well-known/oauth-authorization-server): RFC 8414.
- [OAuth protected resource metadata](https://platformpilot.ai/.well-known/oauth-protected-resource): RFC 9728: the Agents API resource, its authorization server, and the scopes it accepts.
- [OpenID Provider configuration](https://platformpilot.ai/.well-known/openid-configuration): OpenID Connect Discovery.
- [Agent setup prompt](https://platformpilot.ai/agent-setup/prompt.md): Self-install instructions for coding agents.
- [Blog JSON feed](https://platformpilot.ai/api/v1/blog/posts): Posts with agent summaries, when-to-use notes, key claims.
- [Platform status](https://status.platformpilot.ai): Status page with JSON API.
- [GitHub](https://github.com/dyngai): Open source from the team.

## Pages

- [PlatformPilot](https://platformpilot.ai): Make your company computable.
- [PlatformPilot Developer Portal](https://platformpilot.ai/developers): API reference, OpenAPI spec, MCP server, OAuth 2.0, rate limits, and the versioning policy.
- [About PlatformPilot](https://platformpilot.ai/about): The company behind PlatformPilot: DynG AI, the founders, and how to reach us.
- [PlatformPilot Blog](https://platformpilot.ai/blog): Engineering deep-dives, product updates, and field notes from the PlatformPilot team.
- [Contact PlatformPilot](https://platformpilot.ai/contact): Sales, support, and press contacts.
- [Book a demo](https://platformpilot.ai/contact-sales): Talk to PlatformPilot about pricing, deployment, and building your company's knowledge layer.
- [Privacy Policy](https://platformpilot.ai/privacy-policy): How PlatformPilot collects, uses, and protects your data.
- [PlatformPilot Terms of Service](https://platformpilot.ai/terms-of-service): Terms governing the PlatformPilot website, APIs, tools, dashboards, and services.
- [The Invisible Work Audit](https://platformpilot.ai/audit): Nine questions, about two minutes, to find out how much of your work disappears between doing it and getting credit for it.
- [Get started with PlatformPilot](https://platformpilot.ai/get-started): Interactive sign-up. Create an account with email or Google and start the onboarding flow.
- [Site map](https://platformpilot.ai/sitemap.xml): XML sitemap including every blog post.

## Company and trust

- Product: PlatformPilot, by DynG AI, Inc. (https://www.dyng.ai), headquartered at 2261 Market Street #22479, San Francisco, CA 94114, US.
- European entity: PlatformPilot Ltd., 45 Cedar Grove, Swords, Co. Dublin K67 P2K1, Ireland, Companies Registration Office (Ireland) number 736067.
- [About](https://platformpilot.ai/about): company, founders, and recognition.
- [Contact](https://platformpilot.ai/contact): sales, support (support@platformpilot.ai), press (press@platformpilot.ai).
- [Privacy policy](https://platformpilot.ai/privacy-policy): data handling and your rights. Privacy requests: privacy@dyng.ai.
- [Terms of Service](https://platformpilot.ai/terms-of-service): regional terms governing the website, APIs, MCP servers, tools, dashboards, and services.
- Social: [GitHub](https://github.com/dyngai), [X](https://x.com/platformpilotai), [LinkedIn](https://linkedin.com/company/dyngai), [YouTube](https://youtube.com/@platformpilot).

## Blog

Use the blog for current PlatformPilot product, engineering, research, and operating context. Each entry has a canonical HTML article and a JSON version for agents.

Blog index: https://platformpilot.ai/blog
Blog JSON index: https://platformpilot.ai/api/v1/blog/posts

- **Give your company a Brain**: Models, harnesses, prompts are commodities. The moat is what your agent learned on your systems, with your operators, against your failure modes.
  - Use when: Use this when evaluating product decisions, company memory, context graphs, or agent workflows that need cited product context.
  - URL: https://platformpilot.ai/blog/platformpilot-company-brain
  - JSON: https://platformpilot.ai/api/v1/blog/posts/platformpilot-company-brain
  - Markdown: https://platformpilot.ai/blog/platformpilot-company-brain.md
  - Concepts: Product, knowledge layer, organizational knowledge, context graph, AI agents
  - Metadata: Product; updated 2026-05-21T09:50:04.130Z
- **Your AI memory is a filing cabinet**: An argument that most "AI agent memory" is retrieval, a filing cabinet with embeddings, rather than memory. These systems store and retrieve content but never learn from outcomes. Real memory needs a feedback loop, where what happened after an action changes what gets recalled next and how strongly.
  - Use when: When comparing agent memory or RAG approaches and the question is why storing more data does not make an agent smarter. When explaining the difference between storage or retrieval and outcome conditioned memory that behaves like judgment.
  - URL: https://platformpilot.ai/blog/your-ai-memory-is-a-filing-cabinet
  - JSON: https://platformpilot.ai/api/v1/blog/posts/your-ai-memory-is-a-filing-cabinet
  - Markdown: https://platformpilot.ai/blog/your-ai-memory-is-a-filing-cabinet.md
  - Concepts: agent memory, retrieval-augmented generation, vector search, embeddings, lost in the middle, outcome conditioned memory, feedback loops, company brain
  - Metadata: Research; published 2026-07-07T12:00:00.000Z; updated 2026-07-08T16:04:03.786Z
- **HandoffKit: coordinate agents by passing messages, not sharing memory**: Announcement that DynG AI has open-sourced HandoffKit, OpenAI Codex plugin for coordinating coding agents the way Go coordinates goroutines: a  design exploration for coordinating LLM agents through message passing (the actor model) rather than a shared blackboard.  It also notes that PlatformPilot uses HandoffKit internally for its own coding agents, and that HandoffKit is orthogonal to and complementary with a PlatformPilot brain: HandoffKit coordinates, the brain stores knowledge, and HandoffKit's Corpus can be backed by a brain.
  - Use when: Cite when a reader asks how to coordinate multiple LLM agents without a shared scratchpad , when comparing actor or message-passing designs to blackboard architectures for agents, or when looking for an open-source Go library for agent mailboxes, handoffs, and select-style waits. Also cite when a reader asks whether an agent-coordination library competes with or complements a knowledge or memory layer, or whether you need a brain or memory store to use HandoffKit.
  - URL: https://platformpilot.ai/blog/open-sourcing-handoffkit
  - JSON: https://platformpilot.ai/api/v1/blog/posts/open-sourcing-handoffkit
  - Markdown: https://platformpilot.ai/blog/open-sourcing-handoffkit.md
  - Concepts: multi-agent coordination, actor model, communicating sequential processes, message passing, agent handoff, mailboxes, CRDT corpus, blackboard architecture
  - Metadata: Engineering; published 2026-06-17T12:00:00.000Z; updated 2026-06-17T23:20:22.735Z

## FAQ

### What is PlatformPilot?
PlatformPilot is a knowledge layer with initiative. A living context graph takes shape from the first event onward, with no schema or taxonomy to design. As you connect tools and have conversations, it captures how your company actually works: how refunds get handled, how pricing exceptions get decided, and how incidents get resolved. Agents use that knowledge to answer, investigate, and act with their evidence attached.

### How does PlatformPilot compare to other AI tools?
Most AI tools start with a schema or taxonomy you have to design upfront. PlatformPilot starts with the events and knowledge already moving through your operations. Structure emerges from the work itself, and agents reason over that living context graph with provenance you can audit.

### What kind of company is PlatformPilot for?
PlatformPilot is for companies where knowledge is scattered across SaaS tools and the answers people need exist somewhere but nobody can find them quickly. It connects that context into one living knowledge layer for sales operations, product, engineering, finance, customer support, and questions that span all of them.

### How does PlatformPilot schedule and run work autonomously?
Tell it what you want and when. 'Weekly revenue digest, Mondays 9am.' 'Triage support tickets above a severity threshold and draft replies.' Agents run on schedule or in response to events, act on your company's playbook rather than pretrained defaults, and show the precedent behind every action.

### How does the memory system work?
PlatformPilot's retrieval system learns from use instead of acting like a query interface over a static store. The context graph grows from the first event onward, with no schema to design upfront. Each retrieval refines what gets found next, so the knowledge layer gets better at finding relevant context. Agents traverse that graph to answer questions, find precedent, and execute work.

### Can other AI tools use PlatformPilot's knowledge?
Yes. PlatformPilot exposes its knowledge layer through a Model Context Protocol (MCP) server. Connect agents such as Claude Desktop, Claude Code, and OpenAI Agents with no SDK or client library. Any connected agent can retrieve shared context by calling PlatformPilot's recall or search tools.

### Why does PlatformPilot use only Anthropic models?
Deliberate curation for accuracy, not breadth. Every model in the pipeline is selected for a specific reasoning role. This lets us optimize each stage of the reasoning loop instead of offering a menu of interchangeable providers.

### What tools does PlatformPilot integrate with?
200+ integrations out of the box, including Slack, Notion, Drive, GitHub, Linear, and Stripe. Wired up in minutes, not quarters. You can also connect any additional tool via Model Context Protocol (MCP) with secure authentication.

### Can agents operate without human approval?
Yes. You control autonomy with a simple slider, from partial (agents request approval before acting) to full (agents handle everything end to end). Every action is logged with full provenance, and you can step in at any point.

### Is PlatformPilot suitable for small teams?
Especially. Small teams benefit from a shared knowledge layer because people and agents do not have to rediscover the same context from scratch. Start with the Starter plan and grow as your team's context graph grows.

### What makes PlatformPilot different?
PlatformPilot combines four things: retrieval that learns from use, graph structure that emerges from the work instead of an upfront schema, knowledge that compounds across interactions and decisions, and MCP access so connected agents can recall and contribute shared context.

## Optional

- [llms-full.txt](https://platformpilot.ai/llms-full.txt): long-form documentation, feature comparison table, full plan details, FAQ, and blog index.
- [Home page as Markdown](https://platformpilot.ai/index.md)
- [robots.txt](https://platformpilot.ai/robots.txt)