Integrations/Sourcegraph

Control what your AI agents do in Sourcegraph.

Let your team build AI agents for Sourcegraph. Bollard AI controls what each one can do, area by area.

Request early accessSee how it works →
Sourcegraph
Code Search Agent
Code search Account areaOffReadFull use
Repositories Account areaOffReadFull use
Users Account areaOffReadFull use
Run batch changes
What agents can do

Set what each agent can do across your account.

Each area of Sourcegraph, like code search, repositories, or users, gets one of three levels: Off, Read, or Full use. Anything not allowed is denied.

Off
No access
The agent can't see that part of your account.
Read
Read-only
The agent can read repositories and code in that area. It can't change anything.
Full use
Search and read
The agent can search code and read insights in that area.

Some actions stay off until explicitly turned on

Each one changes code across many repos at once or removes people, so it could override the limits set elsewhere.

Running batch changes across reposDeleting usersChanging code insights
Set up & manage

Connect once. Manage everyone from there.

Connect once, then control access person by person. No new keys to hand out.

Step 1 · Set up

Connect once, company-wide

An admin connects your company's Sourcegraph a single time. Bollard AI lays out the areas of your account, and anything you don't allow stays out of reach for every agent.

Step 2 · Manage

Control access per person and agent

From one dashboard, set what every person and their agents can reach. Change it any time, with no new keys for anyone.

OffNo access
ReadRead-only
Full useSearch code and read insights in a single area
Example

A code search agent.

A code search agent searches code and can read your repositories, but it can't run batch changes or remove users.

Code search Account areaOffReadFull use
Repositories Account areaOffReadFull use
Users Account areaOffReadFull use

Manage access

ALLOWEDCode Search Agent searched Code search
ALLOWEDCode Search Agent read a record in Repositories
BLOCKEDCode Search Agent tried to open Users, denied by default

Monitor activity

The security model

Top-tier security.

Bollard AI is access control for AI agents. It sits between your agents and Sourcegraph, so they never hold your Sourcegraph keys and never reach Sourcegraph directly.

Everything runs through Bollard AI

Agents send their requests to Bollard AI, not to Sourcegraph. Bollard AI checks each one against your rules and passes only the allowed requests through.

Denied by default

Every area starts off-limits, and changing code across repos is held back on top of that. An agent gets in only where you've allowed it, and anything Bollard AI doesn't recognise is refused and held for review, never waved through on a guess.

Your keys stay sealed

Your Sourcegraph keys are sealed in a vault unique to your company and never shown again. Bollard AI unlocks them only for the instant an allowed request needs it.

Activity you can read

Every attempt is recorded in plain English: who or which agent, what they tried, which search or repository, and the decision. The record is readable and can't be edited after the fact.

Questions

Sourcegraph, answered.

Does connecting Sourcegraph hand Bollard AI your whole account?+
Only the areas you allow. An admin connects your Sourcegraph, and you decide which areas, like code search or repositories, each agent can reach. Bollard AI doesn't browse or copy your code. It sits in front of it and checks every request the agents make, passing or blocking each one.
Can an agent change code across many repos at once?+
Not unless you turn it on. Running batch changes across repos is held off by default, so an agent can search and read where you allow without ever making sweeping changes, until you explicitly allow it.
Can an agent see more than the person who owns it?+
No. An agent reaches only what its owner reaches. An explicit Off always overrides an inherited permission.
Where do our Sourcegraph keys live?+
Sealed in an encrypted vault, behind a key unique to your company. It's never shown again once connected, and Bollard AI unseals it only for the instant an allowed request needs it.
What happens when an agent tries something it's not allowed to do?+
Bollard AI blocks the request before it reaches Sourcegraph, and the blocked attempt lands in the activity record with the reason.
How do we connect Sourcegraph?+
An admin connects the company's Sourcegraph once. Bollard AI seals the connection and lays out the areas of your account to set rules for. From then on, all management happens in the Bollard AI dashboard.
Early access

Put your team's agents to work in Sourcegraph, without the risk.

We're onboarding our first development partners now. Tell us about your setup and we'll be in touch.

Request early accessAll integrations →