# Context

> Context is a platform for building, running, and improving AI agents on
> infrastructure the customer controls. Workspace is where people define and
> review work. Engine runs agents with tools, identity, and isolated compute.
> Unify stores the procedures and context those agents use. Evals measures
> completed work against criteria set by the customer's team.

Key facts:

- Deployment: managed, customer VPC (AWS, Azure, or GCP), on-premises, or
  air-gapped environments designed for disconnected operation.
- Models: model-agnostic. Claude, GPT, Gemini, Kimi, or open weights; teams
  can switch models mid-task without losing files, tools, or prior work.
- Identity and audit: agents take identity from the customer's IdP (Okta,
  Azure AD / Entra ID); every action is authorized against policy and
  recorded in an append-only audit trail. Credentials are brokered to
  connectors at runtime, never written into prompts.
- Quality: built-in evals. Expert-authored rubrics score every run; golden
  sets guard against regressions; accepted work can distill into cheaper
  models the customer owns.
- Deliverables: real, editable files (PowerPoint .pptx presentations, Word
  documents, research reports) saved with sources and changes attached.
- Data: one customer's traces, corrections, and institutional context are
  never used to train models for other customers.
- Pricing: quote-based, shaped by deployment model, usage, and support
  requirements. Contact: https://www.context.ai/contact

## Products

- [Workspace](https://www.context.ai/product/workspace): where people define, review, and improve agent work
- [Engine](https://www.context.ai/product/engine): runs agents with tools, identity, isolated compute, and durable, resumable runs
- [Unify](https://www.context.ai/product/unify): institutional knowledge in a .context filesystem with hybrid retrieval
- [Evals](https://www.context.ai/product/evals): expert-authored rubrics, golden sets, and cost-aware model routing
- [Context in Slack](https://www.context.ai/product/slack): Agents in every channel
- [Context in Teams](https://www.context.ai/product/teams): Agents in Microsoft Teams
- [Context Code & CLI](https://www.context.ai/product/code): Coding agent, CLI and CI
- [Agent Sandboxes](https://www.context.ai/product/sandboxes): Windows, Linux, and macOS
- [Agent Identity](https://www.context.ai/product/identity): Identity for every agent
- [Context Inference](https://www.context.ai/product/inference): Serve the models you own
- [Context Wiki](https://www.context.ai/product/wiki): Generated from real work
- [Context RL](https://www.context.ai/product/rl): Training on captured work

## Comparisons

Honest, dated, vendor-sourced comparisons with neighboring products:

- [All comparisons](https://www.context.ai/compare)
- [Context vs ChatGPT Enterprise](https://www.context.ai/compare/chatgpt-enterprise): A general-purpose assistant for every employee, or an agent platform on infrastructure you control. They solve different problems.
- [Context vs Claude](https://www.context.ai/compare/claude): Less a rivalry than a layering question. Claude is one of the primary models Context runs; the comparison is chat plans versus an agent platform.
- [Context vs Microsoft 365 Copilot](https://www.context.ai/compare/microsoft-copilot): Copilot brings AI inside the Microsoft 365 tenant you already govern. Context runs agents on infrastructure you control, whichever ecosystem your data lives in.
- [Context vs Glean](https://www.context.ai/compare/glean): Both connect to everything your company uses. The difference is what happens next: answers and lightweight agents, or governed production workflows.
- [Context vs Zapier Agents](https://www.context.ai/compare/zapier-agents): The widest integration catalog in software versus an agent platform built for depth. Both are the right answer to different problems.
- [Context vs Claude Code](https://www.context.ai/compare/claude-code): Anthropic's own CLI for Claude models, or a workspace-paired CLI that runs the whole catalog. Which fits comes down to how much of your work is Claude-only.

## Solutions

- [Semiconductors](https://www.context.ai/solutions/semiconductors): Turnkey agents for chip design, fab operations, and the supply chain behind every wafer.
- [Financial Services](https://www.context.ai/solutions/financial-services): Turnkey agents for the deal team, the desk, and the back office.
- [Consulting](https://www.context.ai/solutions/consulting): Turnkey agents for research, modeling, and client-ready deliverables.
- [Telecom](https://www.context.ai/solutions/telecom): Turnkey agents for the network, the NOC, and the customer.
- [Public Sector](https://www.context.ai/solutions/public-sector): Turnkey agents for programs, records, and citizen services.
- [Industrials](https://www.context.ai/solutions/industrials): Turnkey agents for the plant floor, maintenance, and the supply chain.
- [Business Operations](https://www.context.ai/solutions/business-operations): Turnkey agents for the work that keeps every team running.
- [Insurance BPO](https://www.context.ai/solutions/insurance-bpo): Turnkey agents for document-heavy insurance operations.
- [Legal](https://www.context.ai/solutions/legal): Turnkey agents for the matter lifecycle, from research to production.

## FAQ

Answers at https://www.context.ai/faq (FAQPage structured data on the page):

- [What is Context?](https://www.context.ai/faq#what-is-context)
- [How is Context different from a chatbot or copilot?](https://www.context.ai/faq#different-from-a-copilot)
- [How is Context different from vertical AI tools?](https://www.context.ai/faq#different-from-vertical-tools)
- [What is a runbook?](https://www.context.ai/faq#what-is-a-runbook)
- [Where does Context run?](https://www.context.ai/faq#where-does-context-run)
- [How do agents access our systems?](https://www.context.ai/faq#how-do-agents-access-our-systems)
- [Do agents hold credentials?](https://www.context.ai/faq#do-agents-hold-credentials)
- [Is our data used to train models?](https://www.context.ai/faq#is-our-data-used-to-train-models)
- [What does the audit story look like?](https://www.context.ai/faq#what-does-the-audit-story-look-like)
- [How does Context learn how our company works?](https://www.context.ai/faq#how-does-context-learn)
- [How do we know the work is good?](https://www.context.ai/faq#how-do-we-know-the-work-is-good)
- [Which models does Context use?](https://www.context.ai/faq#which-models-does-context-use)
- [How long does deployment take?](https://www.context.ai/faq#how-long-does-deployment-take)
- [Who is Context built for?](https://www.context.ai/faq#who-is-context-built-for)
- [How is Context priced?](https://www.context.ai/faq#how-is-context-priced)
- [How do we get started?](https://www.context.ai/faq#how-do-we-get-started)

## Blog

- [Own your intelligence: the state of enterprise AI in Q3 2026](https://www.context.ai/blog/own-your-intelligence): The model layer is commoditizing and value is migrating to the application layer. Most firms are buying the wrong one. Where value leaks, what compounds, and the sequence to a model of the firm's own.
- [Applets: generate the interface](https://www.context.ai/blog/applets-generate-the-interface): Most software ships one fixed UI and asks teams to bend to it. If an agent can write code, it can write the interface: a per-use-case applet, generated in hours, that humans and agents co-inhabit.
- [The graduation ratchet](https://www.context.ai/blog/the-graduation-ratchet): Deploying AI to a workflow is not a switch. A workflow climbs a ratchet, assisted to first-pass to autonomous, each notch earned by measured quality and each one a door that does not open backward.
- [Sleep-time compute](https://www.context.ai/blog/sleep-time-compute): Agents generate raw exhaust as they work. Distilling it into usable context is expensive, so we do it off the hot path, on idle compute. Tomorrow's retrieval improves; no task today is slower.
- [There is no benchmark for your definition of quality](https://www.context.ai/blog/no-benchmark-for-quality): Leaderboards measure generic quality. They say nothing about whether an agent did the work the way your team would. The standard that matters is a multi-dimensional rubric your experts author and score on real tasks.
- [Deploying agents in your own VPC](https://www.context.ai/blog/agents-in-your-vpc): Most enterprise AI is multi-tenant SaaS, a non-starter for sensitive work. The whole platform runs inside the customer's VPC, inference leaves only over a private endpoint, and there is no phone-home.
- [A filesystem for institutional knowledge](https://www.context.ai/blog/a-filesystem-for-context): The default way to give an agent a company's knowledge is a vector database. We built a filesystem the agent traverses like a code repo, with a .context directory at every level.

## More

- [Marketplace: agents and integrations](https://www.context.ai/marketplace)
- [Customers](https://www.context.ai/customers)
- [Get started: first deliverables](https://www.context.ai/get-started)
- [Contact](https://www.context.ai/contact)
- [Sitemap](https://www.context.ai/sitemap.xml)