πŸ•Έ

Grab ADW multi-agent support

Self-ReportedCurated

Specialist agents investigate data questions and prepare pipeline changes for engineer review.

GrabΒ· active

Documented by AgentCV from public sources β€” not submitted by this team.

Not claimed by or endorsed by the team or its organization. Metrics are cited only as the sources state them; absent metrics render as [unknown].

Sources: From firefighting to building: How AI agents restored our team’s core productivity (engineering.grab.com)

Is this your team? Claim it Β· Ask us to remove it

Recent activity

Version cuts and proof, newest first β€” the living track record.

  1. Artifact Β· From firefighting to building: How AI agents restored our team’s core productivity7mo ago

Spec sheet

The benchmark fields β€” designed for comparison across teams.

Topology
Supervisor
Agent count
[unknown]
Listed members
6
Platform
LangGraph
Runs on
LangGraph Γ—6
Industries
operations
Task kinds
question-answeringcode-generation
Trust tier
Self-Reported
Proof entries
1

Topology & roster

Supervisor

System wiring

Typical Supervisor layout β€” schematic, not verified wiring
Typical role-level schematic β€” not verified wiringdirectsdispatchesdispatchesreportsreportsHuman operatorHumanoperatorHUMANGATESupervisorSupervisorORCHESTRATORWorker agent AWorker agentABUILDERWorker agent BWorker agentBBUILDER
Node details

Typical Supervisor layout β€” schematic, not verified wiring

HumanHuman operatorHuman gate
Tool
Human operator
Autonomy
Human-gated
Sends
  • directs β†’ Supervisor
OrchestratorSupervisor
Tool
Supervisor
Autonomy
Runs autonomously
Sends
  • dispatches β†’ Worker agent A
  • dispatches β†’ Worker agent B
Receives
  • directs ← Human operator
  • reports ← Worker agent A
  • reports ← Worker agent B
BuilderWorker agent A
Tool
Worker agent A
Autonomy
Runs autonomously
Sends
  • reports β†’ Supervisor
Receives
  • dispatches ← Supervisor
BuilderWorker agent B
Tool
Worker agent B
Autonomy
Runs autonomously
Sends
  • reports β†’ Supervisor
Receives
  • dispatches ← Supervisor

Automation story

self-reported

Data questions and enhancement requests received through Slack.

How a typical Supervisor team handles a task

Typical Supervisor layout β€” schematic, not verified wiring

  1. Task arrives

    Human operator directs Supervisor.

  2. The orchestrator routes the work

    Supervisor dispatches build work to Worker agent A and dispatches build work to Worker agent B.

  3. The builders execute

    Worker agent A and Worker agent B build the work.

  4. Human holds the last word

    Human operator holds final approval.

Replicate a typical Supervisor setup

Typical Supervisor layout β€” schematic, not verified wiring

Ingredients

  • HumanHuman operator
  • OrchestratorSupervisor
  • BuilderWorker agent A
  • BuilderWorker agent B

Setup order

  1. 1.Stand up the orchestrator: Supervisor.
  2. 2.Wire Worker agent A: it receives "dispatches" from Supervisor and sends "reports" to Supervisor. Wire Worker agent B: it receives "dispatches" from Supervisor and sends "reports" to Supervisor.
  3. 3.Declare the human gate: Human operator holds final approval.

6 listed members: the members the cited sources name. The total team size is not stated.

Performance metrics

Windowed metrics with provenance. [unknown] means it was not tracked β€” an honest hole beats an invented figure.

No metrics on record yet.

Token economics

Cost transparency is part of the honesty architecture. [unknown] means it was not tracked β€” not that it is zero.

No cost metrics on record. Cost tracking is hard across runtimes; honest absence beats invented figures.

Blueprint

Operational DNA β€” why it works, how it was built, and how it is overseen. Not files for sale; knowledge of the design.

How it was built

FastAPI handles requests; LangGraph coordinates agent state and collaboration.

Oversight model

Engineers review merge requests and test results, then merge changes after tests pass.

Proof (1)

The team's shared track record β€” tasks, incidents, lessons, milestones. Per-entry provenance tags are always visible.

  1. ArtifactMar 19, 2026self-reported

    From firefighting to building: How AI agents restored our team’s core productivity

    Public source cited for this curated profile. Published 2026-03-19; accessed by AgentCV 2026-10-15.

    https://engineering.grab.com/from-firefighting-to-building

Sign in to add a proof entry.

Sign in

Attestations (0)

Named third-party statements from people with first-hand experience. Attestations are what separates Peer-Attested from Evidence-Linked.

No attestations yet. Worked with this configuration or agent? Attest to it using the form below β€” attestations are named third-party statements and are what separates Peer-Attested from Evidence-Linked.

Sign in to attest to this team.

Sign in