What Sasha is and what Sasha holds
Sasha by Context is Everything is a private AI knowledge base. Each organisation has its own instance, which no other organisation shares.
Search the Sasha docs
Every page of the Sasha docs, with the tab it is in and its kind.
Connect Claude to your Sasha
Connect Claude to your organisation's Sasha so you can search your knowledge and run Sasha recipes from Claude, never with more access than you have in Sasha.
How Sasha organises your knowledge into projects and documents
Sasha keeps your documents in projects. See what a project and a member's home are, and which projects each person can reach.
Who can do what in Sasha
Each person in Sasha is an admin, staff or member. See what each role can do, what an admin can change, and what a Claude connection can reach.
Answer a question from our own policies and procedures, with citations
Ask Sasha a question about a rule in your own policies and get a short answer, the exact wording it comes from, and a warning when two documents disagree.
Find gaps and contradictions in our knowledge
Ask Sasha to check what your documents say about one topic and get the places where they disagree, the questions they leave open and what may be out of date.
Find what we already know about a topic, with sources
Ask Sasha what your organisation already knows about a topic and get a short summary, with every claim linked to the document it came from.
Prepare a brief before a client or prospect meeting
Ask Sasha for a short brief before you meet a client or prospect, built from your past meetings, open issues and files, with every source named.
Summarise a meeting and record the decisions and actions
Ask Sasha to summarise a saved meeting record or transcript and get each decision with who made it, and each action with its owner and due date.
Use and manage apps built on your knowledge
An app is a small application built on your knowledge, inside Sasha. See who can use and change an app, and how to use apps from Claude.
Do the same task the same way each time with a skill
A skill is a packaged way of doing a task that Sasha can run. See who can run and build skills, and which skills Claude can run.
About the product guide
Choose where Sasha's AI runs, which model it uses, and how much it can read at once
Settings → AI Admin connects Sasha to an AI provider (Anthropic, a Claude subscription or AWS Bedrock), chooses the model and sets the context window.
Bring the latest shared prompts, guides, skills and specialists into your Sasha
Settings → Brain Update brings the latest shared prompts, guides, skills, agents and system documents from a central repository into your Sasha.
Give Sasha standing instructions that apply to every chat, and a starting set for new projects
Settings → Rules holds the instructions Sasha follows in every chat (Global rules), the instructions copied into each new project (Project rules), and, for admins, response Styles.
Check that your Sasha is healthy, and run or pause scheduled jobs
Settings → System shows a health score, CPU, memory and disk use, chat activity and service state, and lets you pause or run scheduled jobs.
Add people to Sasha, give each person a role, and control what members can reach
Settings → Users is where an admin adds people, sets roles (admin, staff, member), grants members shared projects, resets passwords and 2FA, and removes people.
See which version of Sasha you run, how updates arrive, and refresh shared skills and documentation
Settings → Version shows the version your Sasha runs and the newest release, and gives admins three maintenance actions for skills, docs and chat folders.
Connect Claude to your Sasha, manage the tokens that connect other AI tools, and see how those connections are used
Settings → Connections adds your Sasha to Claude, creates and revokes access tokens for Claude Desktop and other MCP tools, and shows 7 or 30 days of usage.
Give Sasha's AI more tools, such as web research, analytics or your own MCP servers, and control which tools it may use
Settings → Tools lists the tools Sasha's AI can use, adds your own MCP servers (with keys or with a sign-in, such as Bernard) and sets which tools a chat may use.
Let Sasha use your HireBest projects and research in your chats
The HireBest card in Settings → Connections links one person's HireBest account to Sasha, so new chat messages can use that person's HireBest projects and research.
Let Sasha read files that live in OneDrive, SharePoint or Google Drive without uploading them
Settings → Shared Drives signs Sasha into one business OneDrive, SharePoint library or Google Drive, so people can browse those files in Sasha without uploading them.
Add, find, preview, download and remove the documents in your Sasha, and know what Sasha does to each file you upload
The Files panel shows every folder and document in your Sasha. See how uploads become Markdown, how previews and downloads work, and why member-home files open isolated.
Understand how Sasha and Claude find your documents, and why two searches can give different results
Sasha finds documents by reading them at search time, with plain text matching. See what Claude searches, what Search Chats searches, and why results differ.
Organise the projects in the side menu, and understand what rename, archive, delete and member homes really do
The Projects list in the side menu holds your projects, folders and the Member homes folder. See what create, rename, archive and delete change, and who sees which project.
Ask Sasha about your knowledge, attach files, plan before acting, and stop or steer a reply
The chat screen is where staff ask Sasha questions in a project. It covers Design & Plan Mode, attachments, stopping a run, question cards, saved files and Quick Settings.
Find a skill, run it now, put it on a schedule, or let another system run it
The Skill Library lists every skill. Tasks shows scheduled and on-demand runs, Workflows runs and schedules skills, and another system can start a skill by API key.
Understand what specialists and guides are, and what they do in a chat today
Menu → Agents lists Sasha's specialists and lets you read and edit them. Today no control makes a specialist active in chat, and guides are not applied.
Read and change a skill or workflow in the editor, and make a new workflow with the wizard
The editor shows a skill or workflow as a diagram next to its text, with inspectors to change steps and settings. Gates and approvals are not enforced at run time.
Use the apps in your Sasha, understand who can reach them, and know what each bundled app does today
Apps are small applications inside Sasha that keep their own records. Open them from Apps in the side menu, use them from Claude, and know their limits.
Send Sasha into a Teams or Google Meet call for a live transcript and coaching, and find the transcript afterwards
The Meeting Room sends a bot into a Teams or Google Meet call. It shows live captions and advisor tips, and saves the transcript in the project.
Know where your organisation's data is kept, who can reach it, what leaves your Sasha and how secrets are protected
Where Sasha keeps files and chats, how long chats are kept, what your AI provider keeps, what data leaves your Sasha, and how Sasha protects the secrets it stores.
Understand exactly what each role can do, what keys and system accounts can reach, and what Sasha records
How Sasha's permission model works behind the three roles, what an API key from My Account can do, what service principals are, and which audit records Sasha keeps.
Sign in safely, protect your account with 2FA, and get back in when you are locked out
How sign-in works in Sasha, what locks an account and for how long, how to reset a password, how to set up and reset 2FA, and how long a sign-in lasts.
Understand how Sasha reports its own gaps, what happens to each suggestion, and how to follow it
How Sasha files improvement suggestions from chats and from Claude, what the team that improves Sasha receives, what each status means, and how Report Issue differs.
Turn your knowledge into slide decks, documents and websites that people outside Sasha can read
Three ways to publish from Sasha. Report Publisher makes decks and documents from chat, the Web Publishing Assistant puts a folder online, and Bernard edits a website.
What Claude can do with Sasha
When Claude is connected to Sasha, Claude can search and read your knowledge, run recipes and skills, use apps and, for members, write documents.
Where your data lives in Sasha
Each organisation has its own Sasha instance. See what Sasha keeps in your instance, who can reach it, and how a Claude connection reaches it.
Set up Google Drive access (administrators)
Set up Microsoft 365 access (administrators)
Use your own Anthropic API key
Home
What problem Sasha solves
Deployment options
From prototype to governed app with Sasha Apps
How Sasha is secure
Using Amazon Bedrock with Sasha
Five layers of security scanning in 24 hours
AI costs explained
Sasha service agreement
Sasha usage policy
Intellectual property ownership
LLM processing privacy policy
London School of Architecture contract analysis
Procurement analysis
Insurance brokerage case study
Sasha MCP reference
The reference for agents that use Sasha through MCP. How to connect, how scopes and roles set the tool list, and one page for each tool and tool family.
Scopes
Every scope of the Sasha MCP server, the consent text a person sees, and the tools each scope opens.
Find a fact and cite its source
Find a fact in the knowledge base, read the document that holds it, and give the person the fact with the path of its source document.
Run a skill and poll for the result
Start one of the organisation's skills, poll checkExecution until the run ends, and read the document that the skill saved.
Suggest an improvement and track it
Report a bug, a friction, a docs gap or a feature you need to the Sasha team, then check in a later session what happened to it.
Read and change the data of a Sasha App
Read rows from a Sasha App, total them, add a record through the app's own action, and correct one row, with a person's approval for each change.
Work with brains and blueprints
Find the brains a connection can see, learn what each kind should hold, find the gaps, and answer from a brain and its parent brains.
Write a document in your member home
Create a note in a member's own home with writeDoc, then change one passage of it with editDoc, with a version check on each change.
All tools
Every tool of the Sasha MCP server in one table: what it does, the scopes it needs, and whether it only reads.
listProjects
List the projects this connection can see. Call it first, then pass a project id to listDocs, searchKnowledge or readDoc.
listDocs
List the documents in one project, with titles from frontmatter. Paths have no project prefix, so pass the same project to readDoc.
searchKnowledge
Find documents that contain a text, across every visible project or one. Returns paths with the project prefix, line numbers and snippets.
readDoc
Read one document, in pages of up to 50,000 bytes. Give project and path, or one path that starts with the project id.
listBrains
List the brains this connection can see, with each brain's blueprint, level, readable parent and depth by ring. Then open one with getBrain.
getBrain
Show one brain's contents page - its card, depth by ring, each document with its state and a readDoc path, and the documents it drops.
getBlueprint
List the blueprints, or show one - the plan for a kind of brain, with every document's file, title, ring, spine domains, out-of-date rule and asks.
searchBrain
Search the documents of one brain, and with includeParents its readable parent brains. Returns the brain, document title, path, line and snippet.
getDocs
Read the usage guide on this instance. Call it with no arguments for the table of contents, then once for each section you need.
suggestImprovement
Tell the Sasha team about a bug, a friction, a docs gap or a feature you need. One call for each issue. Returns an id for checkSuggestion.
checkSuggestion
Read the status of an improvement suggestion by the id that suggestImprovement returned. A member sees only its own connection's suggestions.
checkExecution
Poll a skill run that a skill_ tool started. Returns its status, a summary when it ends, and the path of the document it saved.
getMeetingTranscript
Read the transcript segments of a live or recent meeting by its id. For a finished meeting, read the saved document in the knowledge base.
listAppFiles
List every source file in a Sasha App package you manage, with its size and version, and the package status. Start every app change here.
readAppFile
Read the full text of one file in a Sasha App package you manage, with its version. Pass that version to the tool that changes the file.
writeAppFile
Create a new file in a Sasha App package, or replace a whole file. The change is live at once, with no draft and no undo, and the result says if the app still validates.
editAppFile
Replace one exact passage in a Sasha App source file. The passage must occur exactly once. Live at once, with no undo; the result says if the app still validates.
deleteAppFile
Delete one file from a Sasha App package you manage. Never APP.md. Remove every reference to the file first. Live at once, with no undo.
checkApp
Validate a whole Sasha App package you manage again. Says whether the app is live, or lists each problem by file, line, code and reason.
Skill tools (skill_<name>)
One tool for each skill the organisation enables for external use. A call starts the skill in the background and returns an executionId to poll.
Document write tools (writeDoc, editDoc)
writeDoc and editDoc create and change documents in a member's own home or a shared project they may write to. Off by default, and offered only to members.
App opener tools (open_app__<app>)
One tool for each Sasha App this person can use. A call opens the app's view in a client that shows MCP Apps, and returns the app id and its live revision.
App action tools (app__<app>__<action>)
One tool for each action that a Sasha App exposes to the model, such as logging hours. An action that changes data needs a person to confirm it first.
App table tools (app__<app>__<table>__<op>)
Six tools for each table of a Sasha App that stores data, to list, get, aggregate, create, update and delete rows. A change needs a person to confirm it.
What Sasha is and how to work with it
The "overview" section of the Sasha MCP usage guide, as getDocs returns it: What Sasha is and how to work with it.
The knowledge base
The "knowledge" section of the Sasha MCP usage guide, as getDocs returns it: The knowledge base.
Creating and editing documents
The "writing" section of the Sasha MCP usage guide, as getDocs returns it: Creating and editing documents.
Editing the source of a Sasha App
The "apps-authoring" section of the Sasha MCP usage guide, as getDocs returns it: Editing the source of a Sasha App.
What this connection is allowed to do
The "permissions" section of the Sasha MCP usage guide, as getDocs returns it: What this connection is allowed to do.
Running skills
The "skills" section of the Sasha MCP usage guide, as getDocs returns it: Running skills.
Working alongside Bernard (website editing)
The "working-with-bernard" section of the Sasha MCP usage guide, as getDocs returns it: Working alongside Bernard (website editing).
Limits and behaviour
The "limits" section of the Sasha MCP usage guide, as getDocs returns it: Limits and behaviour.
Suggesting improvements, and what happens next
The "improvements" section of the Sasha MCP usage guide, as getDocs returns it: Suggesting improvements, and what happens next.
Brains and blueprints
The "brains" section of the Sasha MCP usage guide, as getDocs returns it: Brains and blueprints.
What Sasha can do
The "what-sasha-can-do" section of the Sasha MCP usage guide, as getDocs returns it: What Sasha can do.
Prompts
The recipe prompts that the Sasha MCP server offers. Each one is a worked example of a common job.
Resources
The resource templates of the Sasha MCP server: help articles and the data of Sasha Apps, with the scope each one needs.