Skip to content
0727
InsightsAcademyCasesEventsSign in
中文/EN
Cases/Grab
← Back to cases
← Previous10 / 127Next →

Grab

From a technical support bot to the enterprise LLM-Kit agent platform
First-party enterprise source Mobility and local-services platform Enterprise deployment ⚙ Technical reference Deep case | Key delivery chain is substantially documented Evidence level A Enterprise agent platform at scale
A Evidence level
Agent platform (Part 1): How we help Grab build and run AI agents at scale
Publisher: Grab Engineering · Company engineering blog · Direct case-level source
Claim origin: Company engineering team disclosure · Independent verification: No · Accessed: 2026-09-19
Evidence level measures whether a source can be located and reviewed; it does not mean vendor-reported claims were independently audited.
Deep case | Key delivery chain is substantially documented 12 / 12
Business context2 / 2
Transformation workflow2 / 2
Technical workflow2 / 2
Human roles & governance2 / 2
Measured outcomes2 / 2
Source traceability2 / 2
All six dimensions meet the current completeness threshold.
Grab shows how repeated production failures in one internal support bot became an enterprise agent framework that packages authentication, tools, observability, evaluation, and deployment into a reusable starting point.
Business problem

Grab’s technical infrastructure team handled thousands of repeated support tickets in a six-month period. Its early support bot could answer questions, but every new agent team still had to rebuild authentication, secrets, deployment, observability, tool integration, and evaluation—making it difficult to move prototypes reliably into production.

Solution

Grab first built a Go-based Level-0 support bot whose single-agent loop could call Glean, Kibana, GitLab, Slack, and HTTP tools, then escalate unresolved requests to a person with context attached. The team converted those production lessons into LLM-Kit: a template that generates a production-ready repository with FastAPI, LangGraph ReAct agents, remote MCP, pgvector, Vault, OIDC, OpenTelemetry, tests, and evaluations.

Technical architecture & production workflow
Step 01
Documentation, runbooks, Slack, Jira, logs, and GitLab files
→
Step 02
Glean retrieval with Kibana, GitLab, Slack, and HTTP tools
→
Step 03
LangGraph ReAct loop with remote MCP tool discovery
→
Step 04
Shared LLM gateway, model routing, and usage governance
→
Step 05
FastAPI, Postgres/pgvector, Vault, OIDC, and environment configuration
→
Step 06
OpenTelemetry observability plus golden sets, ROUGE, BLEU, and LLM-as-a-judge evaluations
Key technology & infrastructure components
LLM-KitLangGraphFastAPIMCPGleanPostgres / pgvectorVault / OIDCOpenTelemetryEvalshub
Human roles & accountability

The bot attempts documented questions first and routes unresolved tickets to the right technical team with context. Agent developers own business logic and domain tools; the platform team owns authentication, secrets, deployment, gateways, observability, and the shared evaluation foundation.

FDE delivery actions
  • Use one high-volume support workflow to expose production agent problems
  • Separate the reasoning plane from the tool plane
  • Turn authentication, secrets, storage, and deployment into a reusable template
  • Start developers from working agents rather than an empty project
  • Ship golden tests and multiple evaluators on day one
Reusable delivery patterns
  • At scale, the bottleneck is usually production engineering—not the first demo
  • A shared framework should standardize plumbing while preserving domain-logic flexibility
  • Both MCP tools and model calls need enterprise registration and governance
  • Evaluation should ship with the template rather than be added before launch
Business outcomes & delivery results

Grab reports that more than 500 services run on its internal agent framework, more than 50 remote MCP servers are registered, and the shared LLM gateway handles billions of tokens per month. Day-one production wiring that previously took at least two weeks now takes about one hour.

Evidence boundaries & verification notes
  • “500+ services” is retained as reported and should not be read as 500 distinct agent products.
  • The two-weeks-to-one-hour metric covers day-one production wiring, not complete agent delivery.
Primary source: Agent platform (Part 1): How we help Grab build and run AI agents at scale ↗
Traceable does not mean independently audited
Open primary public source
0727.ai · Trusted agents, built together.Case research: FDE-case-library ↗ · MIT