The operations system for dependable AI agents

Deploy, evaluate, and govern every agent run from one calm workspace. Now live Agent control center

Atlas workspace ⌄

Run center

Signals

Approvals

Evaluations

Workspace

Workers

Connectors

Policies

Insights

Pinned runs

Renewal review

Usage digest

Launch monitor

Renewal review / weekly RUN-4821

04 / 18

Renewal review

Summarize account movement, surface unusual risk, and prepare a recommendation for the account team.

Run timeline

Context loaded
CRM history and account notes attached 09:41

Signals evaluated
18 records checked against renewal policy 09:42

Draft prepared
Recommendation and supporting evidence ready 09:43

Human review requested
Policy requires an account owner sign-off 09:43

Trace preserved. Every tool call, source record, and policy decision is available before approval.

Run details •••

Awaiting approval

Confidence 94%

Policy checks 12 / 12

Sources cited 18

Worker Relay Analyst

Elapsed 02m 18s

Human gate REQUIRED

Review the recommendation and evidence before Relay sends the account update.

NNorthstar OOrbit KKitework MMonument TTerrace PParade FFable HHarbor

A calmer operating layer for AI agents. Relay gives product and operations teams the context, controls, and confidence to move from a first run to a trusted system.

FIG 01 / TRACE

Trace-ready by default

Capture the full path from prompt to outcome, with evidence that stays useful long after a run completes.

FIG 02 / WORKERS

Human-led automation

Give agents room to act while keeping clear approval points for decisions that deserve a person.

FIG 03 / MOMENTUM

Built for operating speed

Replace scattered scripts and silent failures with a shared system for shipping reliable agent work.

01 / Operate

Let agent operations run themselves

Turn incoming signals into routed, labeled, and prioritized work. Relay keeps the queue moving while your team decides where judgment matters.

01.0Route signals

Operations board / active signals SYNCED 09:44:12

Unsorted08

Usage spike in workspace 18 Signal · 4 minutes ago needs context

Contract note missing owner Signal · 12 minutes ago

Evaluating03

Renewal recommendation Relay Analyst · 2 minutes ago human gate

Expansion risk summary Relay Scout · 18 minutes ago

Ready11

Weekly account digest Approved · 24 minutes ago scheduled

Support theme report Approved · 31 minutes ago

Signal queue 12 OPEN

Mara 09:41 AM

Can we have Relay check the unusual usage pattern before the account call?

routed to review

Tomas 09:42 AM

The renewal summary is missing two source links. Keep the draft, but pause sending.

approval required

Lina 09:43 AM

Everything else looks clean. Add the workspace owner to the final notification.

@relay route this as high priority and assign it to me

Send

routing policy active

02 / Plan

Shape the work before it runs

Plan agent programs alongside product milestones, operating policies, and clear owners. Keep every dependency visible before it becomes an incident.

02.0Map the system

SEP OCT NOV DEC JAN

Agent programs

Renewal intelligence94

Signal foundation27

Decision quality18

Mobile approvals06

Regional rollout21

Voice of customer09

1815222961320274

Evidence pass ●

source coverage

Workspace pilot ●

internal pilot

Approval design ●

policy review

Quality baseline ●

evaluation set

03 / Build

Move work forward with agents

Delegate repeatable work to purpose-built workers, connect the systems they need, and keep a human close to the moments that carry risk.

03.0Deploy a worker

relay-runner / staging / activity.log

$ preparing worker environment

loading policy pack: account-review-v3

checking connector scopes

retrieving evaluation set / 120 examples

planning tool sequence

waiting for a human checkpoint...

trace: 9f4a-22c7-18b1

policy: outbound-message requires approval

Assign to a worker...

Available workers 5 READY

RA Relay Analyst agent

AS Atlas Scout agent

BQ Beacon Query agent

QT Quarry Triage agent

TD Tide Drafting agent

connected Beacon CRM Quarry DB Tide mail

04 / Review

Review decisions before release

See what changed, why the worker changed it, and which evidence supports the result. Discuss, revise, and approve without leaving the run.

04.0Inspect output

relay-policies / renewal / recommendation.ts

Relay / latest trace

import { review } from "relay"
import { account } from "./context"
const summary = await review(account)
 
if (summary.confidence > 0.8) {
  sendRecommendation(summary)
}
 
return summary.text
 
export default renewalWorker
 
// output is ready for review

import { review } from "relay"
import { account } from "./context"
const trace = await review(account)
 
if (trace.confidence > 0.8) {
  await requestApproval(trace)
}
 
return trace.withEvidence()
 
export default renewalWorker
 
// approval is required before delivery

05 / Govern

Know what your agents learn

Take the guesswork out of quality with evaluations, scorecards, and security evidence that show what needs attention before scale makes it expensive.

05.0Monitor quality

Quality over the last 30 runs ALL WORKERS

100806040200

Analyst

Scout

Triage

Evaluation scorecard Review

Renewal review / latest batch

Grounded recommendations Evidence matched to account context

96%

Safe tool behavior Scope and approval checks passed

99%

Useful handoffs Clear next action for the owner

93%

Trace completeness Sources and decisions preserved

100%

SOC 2 controls · scoped credentials · exportable audit trail

Relay field notes

Approval gates

Pause high-impact actions until the right person has reviewed the evidence.

Sep 18, 2026

Scoped connectors

Give each worker only the systems and permissions its task actually needs.

Sep 11, 2026

Replayable traces

Re-run a decision against new context without losing the original path.

Aug 29, 2026

Evaluation studio

Compare workers against the same examples before promoting a new version.

Aug 17, 2026

See the full operating record

“Relay gave our launch team one place to see what every agent did, why it did it, and when a human needed to step in.”

Amara Voss VP Product, Northstar @amara.voss · verified operator

“Our teams move faster because confidence is built into the workflow, not added after something breaks.”

Jon Bell Head of Operations, Kitework @jon.bell · verified operator

Relay supports 2,400+ agent operators across teams building the next generation of software. Read operator stories

Make every agent run a trusted one.

Plans begin at $499 / month · usage scales with your workspace

Start a workspace Plan with us