270M LLM powers on-device voice agent at 0.9s latency

Speech-android, an open-source voice agent framework, demonstrates that tool-calling agents can run on consumer phones using a 270-million-parameter FunctionGemma model in just 1.2 GB of RAM. The system chains voice activity detection, streaming speech-to-text, tool-calling LLM routing, device actio...

Sign in to read the full analysis

Free account. Full analysis on LLM unit economics, plus the weekly Cost-of-Inference column.

Get started for free Sign in

Try it on your own context

You just read the writeup. Now run the thing. Paste a doc or some verbose tool output and watch it shrink — free, no signup.

Your text

# Service Operations Runbook: Payments API

## Purpose and scope

This runbook covers the payments-api service: what it does, how it is deployed, what its dependencies are, and what to do when it misbehaves. It is written for the on-call engineer. Every procedure here assumes you have production read access and the ability to trigger a deploy through the standard pipeline. Nothing in this document requires direct database write access, and no procedure here should be improvised under pressure: if the situation is not covered, page the service owner rather than inventing a fix at 3am.

The payments-api accepts charge requests from the checkout frontend, validates them against the pricing catalog, forwards them to the payment processor, and records the outcome in the orders database. It is the only service permitted to talk to the processor. Average traffic is steady during business hours with a daily peak around 19:00 UTC and a weekly peak on Friday evenings.

## Architecture and dependencies

The service runs as three replicas behind the regional load balancer. Each replica is stateless; all persistent state lives in the orders database and the idempotency-key store. The service depends on four things: the orders database (primary and one read replica), the idempotency-key store, the pricing catalog service, and the external payment processor. Of these, only the processor is outside our control.

Dependency failure behavior is deliberate and asymmetric. If the pricing catalog is unreachable, the service serves prices from its local cache for up to ten minutes and emits a degraded-mode metric. If the idempotency store is unreachable, the service refuses new charges entirely, because accepting a charge without idempotency protection risks double-billing, and double-billing is strictly worse than downtime. If the processor times out, the charge is recorded as pending and a reconciliation job resolves it within the hour.

## Deployment

Deploys go through the standard pipeline: merge to main, automated tests, staging deploy, a thirty-minute soak with synthetic checkout traffic, then production rollout one replica at a time. The pipeline aborts automatically if the error rate on the new replica exceeds the old baseline. A full rollout takes about twenty minutes. Rollback is the same pipeline in reverse and takes about six minutes; the on-call engineer can trigger it without approval.

## Monitoring and alerts

Three alerts page the on-call engineer. High charge failure rate fires when more than two percent of charge attempts fail over five minutes; the usual causes are a processor incident or a bad deploy, in that order. Idempotency store unavailable fires immediately on connection failure. Reconciliation backlog fires when pending charges older than ninety minutes accumulate, which usually means the reconciliation job is stuck rather than the processor being slow.

2,912/12,000 chars

Compressed

Compressed text will appear here…

Method & sources

Source type: Primary publication (lab/vendor blog) — our analysis + implication
Source link: r/ai-agents
Published: 2026-11-08 15:47:43 UTC
Byline: By the gotcontext.ai team (editorial standards)
Correction?: corrections@gotcontext.ai

← All Intelligence

Sign in to read the full analysis

Related