Grab standardized 500 internal agent services on one framework called llm-kit and cut the time to…
grab standardized 500 internal agent services on one framework called llm-kit and cut the time to launch a new agent from two weeks to one hour. the insight that wins in production is not a better model but a shared runtime with tool discovery and secret handling built in.
enterprise agents will be won by plumbing, not prompt craft.
Context
Grab Engineering's post of 24 July 2026 says more than 500 services run on its internal agent framework and that day-one wiring that used to take two weeks or more now takes about an hour. InfoQ of 15 September 2026 reports Grab standardized more than 500 internal agent services on LLM-Kit, with evaluation, tracing, secret handling and tool-server connections already wired in, and agents discovering their tools at runtime.
The figures are Grab's own statements, vendor-reported. The count is more than 500, so the note's 500 is a lower bound, not a conflict. The first-party claim is about day-one wiring, not the time to launch a new agent end to end. The line that shared runtime beats a better model is the author's opinion.
Related work
- Earlier note on Grab's agent platform ↗Same Grab story.
Watch next
- Later parts of Grab's agent platform series.
Sources
- How Grab builds and runs AI agents at scale (Grab Engineering, 24 Jul 2026)engineering.grab.com
- Grab agent platform (InfoQ, 15 Sep 2026)infoq.com
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 19 September 2026 at 00:19 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →