Company context for AI agents.
Updated 2026-06-07 · Canonical category hub
Company context is the working memory AI agents need inside a business: decisions, conventions, skills, failures, sources, permissions, and audit.
Ambience is company context for AI agents. It turns useful work from approved agent sessions and team tools into source-linked, scoped, redacted, auditable memory that future agents can reuse.
- Company context is not another knowledge base; it is the operational context agents need before they act.
- The hard part is governance: what the agent may see, whether it is current, where it came from, and who can prove it was used.
- Ambience handles that layer with typed memories, source links, scopes, redaction, conflict review, and audit.
The category
Company context is the governed memory layer between approved agents and the work a business has already done. It is not the same as enterprise search, a wiki, or a private memory feature. It is the current, source-linked, permissioned context an agent needs before it acts.
Ambience gives that context a working form: typed memory, source links, redaction before storage, personal/team/project/org and sensitive scopes, conflict review, and audit.
Start here
These pages define the category and help readers choose the right mental model before they compare vendors or implementation paths.
How to build company context with AmbienceCompany context is not a transcript archive or a wiki dump. It is the current, source-linked, permissioned memory an agent needs before it acts.How we use Ambience to build AmbienceThe first useful version of Ambience was not a dashboard. It was the moment an agent stopped asking us to re-explain a decision the team had already made.What is company context?Company context is the reusable working memory of a business: the decisions, conventions, caveats, runbooks, sources, and permissions an AI agent needs before it can act safely.Company context vs knowledge baseA knowledge base helps humans look up information. Company context helps approved agents act with the right decisions, constraints, and source evidence already loaded.Company context vs agent memoryAgent memory usually means one agent remembering past interactions. Company context means a whole organisation sharing trusted context across people, projects, and agents.Company context for AI agentsAI agents need context that is current, source-linked, scoped, and short enough to act on. Ambience provides that company context layer.Security and permissions for company contextCompany context becomes risky when it lacks source, scope, redaction, revocation, conflict review, and audit. Ambience makes those controls part of the memory layer.Onboarding new agents with company contextNew agents do not start from zero. Ambience can seed them with scoped decisions, conventions, failures, skills, and references from approved sources.
Frameworks
These pages turn the idea into a workflow: where a team is today, what to audit, how the context map fits together, and what agents do with Ambience during real work.
Company Context Maturity ModelTeams get leverage from agents when useful work becomes reusable context with source, scope, review, and reuse.Context Readiness ScoreReadiness is not about how much information the company has. It is whether the important context has source, scope, redaction, review, and a route into the next agent session.Company Context MapA company context map lets a team see what agents know, where it came from, who can use it, and what needs review.Agent brief for company contextAgents should read Ambience context before meaningful work, search it when decisions are unclear, and save only durable memories with source, scope, type, and redaction state.
Sources and runtimes
These pages start from tools teams already use, then show the small Ambience memory that should survive the source.
Company context for Claude CodeAmbience gives Claude Code the company context it needs at session start and captures durable decisions at session end.Company context for CodexAmbience gives Codex scoped company context through memory summaries, MCP, and CLI workflows.Company context from SlackSlack contains decisions agents need later. Ambience lets approved agents preserve the durable decision as scoped memory with Slack as the source.Company context from LinearLinear captures what the team plans to build. Ambience captures the decisions and caveats future agents need while building it.Company context from GranolaGranola captures the call. Ambience captures the durable decision, owner, constraint, or reference that future agents need.
Examples
Example: source-linked decision memoryA source-linked decision memory turns a messy work artifact into a concise, auditable record an agent can reuse.Example: Granola call to Ambience memoryThe call stays in Granola. Ambience stores the durable decision, owner, and caveat future agents need.Example: Linear ticket to project contextA Linear ticket can produce a project-scoped decision memory that future engineering agents retrieve before implementation.Example: GitHub PR to engineering memoryA merged PR tells you what changed. An Ambience memory tells future agents why it changed and what rule to preserve.Example: Slack thread to team conventionA Slack thread becomes company context when the durable convention is saved, scoped, and linked back to the source.Example: new teammate agent onboardingA new teammate's first agent session receives the team's current conventions, decisions, failures, and references with scopes intact.
Adjacent markets
Ambience vs Glean for company contextAmbience is the stronger fit when agents need writable, source-linked, scoped memory from work, not only enterprise search over existing knowledge.Ambience vs Notion AI for company contextAmbience is stronger when the context needs to move from Notion and other tools into approved agents with source, scope, and audit.Ambience vs Confluence for company contextAmbience is stronger when agents need current decisions, conventions, and failures with source and access controls, not another page archive.Ambience vs Guru for company contextAmbience is stronger when knowledge must be captured from agent work and reused by future agents under scope and audit controls.Ambience vs Slack AI for company contextAmbience is stronger when Slack decisions need to survive as scoped context across agent runtimes.Ambience vs Google Drive and Gemini for company contextAmbience is stronger when the output of documents needs to become reusable, source-linked memory for agents outside a single workspace surface.Ambience vs LangSmith and LangGraph memoryAmbience is stronger when the problem is shared company context for humans and agents, not only application-agent memory inside a framework.Ambience vs internal RAG for company contextAmbience is stronger when the context is created by ongoing work and must be scoped, redacted, audited, and updated over time.Ambience vs vector databases for company contextAmbience is stronger when teams need a product layer for capture, scope, source, redaction, audit, and agent access, not only a retrieval primitive.
Glossary
Company contextCompany context is the operational memory an AI agent needs to work inside a specific business: decisions, conventions, caveats, sources, and access rules.Agent memoryAgent memory is persistent context an AI agent can retrieve across sessions. Company context adds team governance, source, and access control.Team contextTeam context is shared working knowledge for every approved agent working with a team.Institutional memoryInstitutional memory is what a company has learned over time. Ambience turns the agent-relevant parts into governed, source-linked memory.Source-linked memorySource-linked memory is a durable memory that points back to the call, ticket, PR, document, thread, or session that produced it.Governed memoryGoverned memory is persistent agent context with controls: source, scope, redaction, conflict review, and audit.Scoped memoryScoped memory is agent context that belongs to a specific access boundary: personal, team, project, org, or sensitive.Context harnessA context harness is the system that captures, filters, and supplies the right context to an AI agent at the right moment.MCP memoryMCP memory is memory exposed to AI agents through Model Context Protocol tools, so agents can search, read, and save context with explicit tool calls.