← All implementations

Browserbase · Task agent

bb

One generalized agent in Slack that writes PRs, investigates sessions, queries the warehouse, logs feature requests, and runs browser agents across engineering, ops, sales, and support.

1

Approach type
Task agent
Work
Coding, Code review, Support, Customer success, Research
Human involvement
Drafts reviewed
Invocation
Event driven, Interactive
Interfaces
Slack, Web, Webhook
Deployment stage
Deployed
Evidence strength
Detailed primary
Entry reviewed

How it works

The workflow the sources report for this implementation.

Markdown playbooks lazy-loaded per task so the general agent stays small

1

Scoped permissions per session limit the actions available to the agent

1

The sandbox runs arbitrary code yet never touches a secret

1

Where people stay involved

  • coding request → reviewed pull requestWork product review · Level 3

Level 3 for coding request → reviewed pull request; human attention boundary: work-product-review.

1

Observation date
2026

Implementation details

Sandbox

Ephemeral Linux VM; pre-warmed snapshot rebuilt every 30 min; idles out after 30 min

1

Harness

OpenCode core loop with 6 tools (read/write/edit/exec/safebash/skill)

1

Model

Frontier models

1

Interfaces

slack, web, webhook

1

Tool access

exec routes through a serverless integration proxy (Snowflake, HubSpot, Pylon, Grafana); the sandbox never sees real secrets

1

Knowledge

Key repos cloned into /knowledge/; skills (markdown) loaded on demand

1

Credentials

Credential brokering; the sandbox boots with references + rotating session tokens only; the proxy holds real creds; egress injection for a few hosts

1

Reported results and limitations

The catalog records what the sources report, with the scope and the denominator of every figure. A qualification below limits the figure it sits under.

Reported metrics

Headline claim

Feature-request pipeline at 100% coverage with zero human effort

1

Reported by
Browserbase
Scope
Automatic feature-request scanning of every closed support ticket and meeting transcript
Denominator
Closed support tickets and meeting transcripts
Key observation

Feature-request pipeline at 100% coverage, zero human effort

1

Reported by
Browserbase
Scope
Automatic feature-request scanning of every closed support ticket and meeting transcript
Denominator
Closed support tickets and meeting transcripts
Key observation

99% of first-response times < 24 hrs

1

Reported by
Browserbase
Scope
Reported support first-response time below 24 hours
Denominator
Support first responses; exact sample and measurement window not provided
Key observation

Session investigation: 30–60 min of log-diving → one Slack message

1

The source does not report the denominator of this figure.

Reported by
Browserbase
Scope
Session investigation initiation: manual log-diving versus a Slack request

Lessons and interpretation

One agent with good abstractions beats a fleet of narrow bots

1

Separate capabilities from the core loop; domain logic lives in skills + service packages

1

Don't trust the model, remove its ability to do wrong: scope tools and services per invocation source

1

Meet people where they are; Slack is the highest-leverage surface because that's where work already happens

1

Sources and research details

Citations link to the original publisher. Each source also keeps a preserved copy in the repository, so a changed or removed page stays checkable.

  1. How we build internal agents at Browserbasehttps://browserbase.com/blog/internal-agentsEngineering blog · First party · Last source verification: 2026-08-31
    Preserved copy ↗
Research details for every claim on this page
  1. Summary
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  2. Headline claim
    Statement type
    Metric
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
    Reported by
    Browserbase
    Scope
    Automatic feature-request scanning of every closed support ticket and meeting transcript
    Denominator
    Closed support tickets and meeting transcripts
    Method
    Not reported
    Observation date
    Not reported
  3. Sandbox
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  4. Harness
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  5. Model
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  6. Interfaces
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  7. Tool access
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  8. Knowledge
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  9. Credentials
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  10. Supporting component
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  11. Supporting component
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  12. Supporting component
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  13. Key observation
    Statement type
    Metric
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
    Reported by
    Browserbase
    Scope
    Automatic feature-request scanning of every closed support ticket and meeting transcript
    Denominator
    Closed support tickets and meeting transcripts
    Method
    Not reported
    Observation date
    Not reported
  14. Key observation
    Statement type
    Metric
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    The source reports 99% below 24 hours with awkward wording; no sample, timestamps, or method is provided.
    Reported by
    Browserbase
    Scope
    Reported support first-response time below 24 hours
    Denominator
    Support first responses; exact sample and measurement window not provided
    Method
    Not reported
    Observation date
    Not reported
  15. Key observation
    Statement type
    Metric
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    A Slack message replaces the manual initiation workflow; the article does not report end-to-end automated investigation latency.
    Reported by
    Browserbase
    Scope
    Session investigation initiation: manual log-diving versus a Slack request
    Denominator
    Not reported
    Method
    Not reported
    Observation date
    Not reported
  16. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  17. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  18. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  19. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  20. Operating model assessment
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    High
    Confidence reason
    The source documents agent-authored pull requests while the enclosing workflow retains human review.
    Observation date
    2026
Back to the directory →