Customers · in production

The teams running real agents on Lattice. Three of them, in their own words.

We don't ship a customer carousel that scrolls past in a banner. We pick three customers per quarter, write up what they actually do, and let their engineers say what works — and what they'd still change.

A subset, with permission ↓
Replicate
Granola
Decagon
Pylon
Cresta
Modal
Linear
Dust
Continue
Resemble
Together
Sonnet
Helix
Ramp
Notion
Cursor

About 60% of our customers ship under NDA. The list above is the public subset. If you'd like a reference call with someone in your category, the team can usually arrange it within a week.

01 · case

Replicate

Model hosting · 12,000+ public models

Replicate uses Lattice to run their internal inference orchestrator — the system that schedules cold starts, autoscales replicas, and routes requests to the right model. Migrated four custom schedulers into one Lattice deployment in six weeks.

4 → 1
Internal schedulers consolidated
94%
Reduction in dead-letter incidents
1.2B
Monthly inference runs through Lattice
1 quarter
On-call hours saved per quarter
replicate.arch·simplified
  request ──► Lattice scheduler ──► replica pool
                  │                      │
                  ▼                      ▼
          retry / DLQ              cold-start cache
                  │                      │
                  └──────► trace ◄───────┘
2026-04-14 09:42info
We migrated four in-house schedulers to Lattice in six weeks. Replays alone have saved my team an entire on-call rotation per quarter.
Sasha Lin · Staff Engineer, Replicate
02 · case

Granola

AI meeting notes · 320,000 users

Granola's nightly enrichment pipeline runs for ~11 hours, processing every meeting recorded that day. Before Lattice, the team paged on retry-storm failures roughly twice a week. After: zero pages in eight months.

11 hr
Average nightly run length
0
On-call pages, last 240 days
$0.0019
Cost per processed meeting
240k
Meetings enriched per night
granola.arch·simplified
  cron 02:00 UTC ──► Lattice run (resumable=true)
                          │
          ┌───────────────┼───────────────┐
          ▼               ▼               ▼
    transcribe     extract topics    generate notes
          │               │               │
          └──────►   write back to DB ◄───┘
2026-03-28 16:11info
Lattice is the only agent infra we evaluated that took the long-running case seriously. Our nightly runs are 11 hours. Nothing else handled it.
Marcus Reid · CTO, Granola
03 · case

Decagon

AI customer support · Series C

Decagon attaches Lattice evaluators to every production agent. They sample 12% of real customer conversations through a faithfulness rubric and a tone rubric, with regression alerts wired into PagerDuty. Caught two model drifts in 2025 before any customer noticed.

12%
Production traffic sampled to eval
2
Model regressions caught pre-customer
47s
Median time from regression to alert
100%
Agent runs traced to OpenTelemetry
decagon.arch·simplified
  customer msg ──► triage agent ──► response
                       │
                       ▼  (12% sample)
                eval rubric · faithfulness
                       │
                       ▼  (score < 0.85)
                  PagerDuty alert ──► oncall
2026-02-19 22:07info
The eval primitive is the thing. We catch model regressions on production traffic before customers do. That has changed how we ship.
Imani Ewell · Lead Eng, Decagon
From the same engineers, unprompted ↓

What our customers wish was different. Verbatim. We publish the gripes.

The Python SDK is a year behind the TS SDK. We use Python.
platform eng, Series B AI startup
shipping parity in v1.5, June 2026
The trace UI is brilliant for one run. Across runs, it's worse than Datadog.
infra lead, Series C SaaS
cross-run analytics in flight; expected Q3
Self-host on K8s is a chart Helm. The chart is rough.
SRE, infrastructure team
Helm chart rewrite + Operator pattern, Q3 2026

Want a reference call? We'll set one up.

Most of our customers will jump on a 30-minute call with a serious prospect. Tell us your category and what you're trying to ship; we'll match you with someone close to your shape.

Get ProposalInstant SEO Audit