Signal Run
Start free
[PULSE AI · GOVERNED AGENTS · NOW AVAILABLE]

Ship governed AI agents on your own data.

Gateway, guardrails, evals, and an immutable audit trail — for every agent you run. Decision-grade, billed by use. No ontology required to start.

Start freeSee a live trace →
NO CARD · 1K RUNS FREE / MO
Agent in a day
connect data → ship governed
Governed by default
guardrails + evals + audit
One gateway, many models
cost · latency · region
Pulse AIagent support-triage ▾
PlaygroundPromptToolsKnowledgeGuardrailsEvalsTracesDeploy
sandbox ▾MC
Agents7
Routines6
Tools18
Models7
Knowledge6
Guardrails14
Evals42
Traces1.4M
Sandbox · build and test before you shipclaude-sonnet-4.6
U
A customer wrote: 'I was charged twice this month, please fix it.' What queue?
Classified → queue: billing · priority: high · sentiment: frustrated. Policy NO_PROMISES held (no refund committed). Suggested first reply drafted.
● governedtrace_4e2a1,204 in · 312 out$0.0091840 ms
U
And this one: 'How do I export my data to CSV?'
Classified → queue: support · priority: normal. Grounded answer found in product_docs (3 chunks). Confidence 0.96.
● governedtrace_51c8980 in · 240 out$0.0071520 ms
Message the agent…Run ↵
[MODEL]
Claude Sonnet 4.6
anthropic1.4 s p99
in $3.00out $15.00 /1M
Claude Opus 4.7
anthropic2.8 s p99
in $18.00out $72.00 /1M
Claude Haiku 3.6
anthropic0.4 s p99
in $0.80out $2.40 /1M
GPT-5.2
openai1.8 s p99
in $5.00out $20.00 /1M
[LAST RUN]
tokens in4,218
tokens out982
cost$0.027
latency2.18 s
eval96.4%
FIG 00 · PULSE AI PLAYGROUND · SANDBOX · ILLUSTRATIVE
01PROOF

Every agent run is governed and provable.

Not a promise — a trace. Span tree, eval pass-rate, and a guardrail decision from a single run.

trace · run_8f3a21c · agent: invoice-triage1,284ms · 7 spans
agent.run
1,284ms
gateway.route → claude-sonnet
12ms
guardrail.input.pii
4ms
tool.query_warehouse
842ms
guardrail.output.policy
6ms
eval.faithfulness
38ms
audit.write
9ms
FIG 01.1 · TRACE SPAN TREE · ILLUSTRATIVE
[EVAL · LAST 7D]
98.2% pass
faithfulness99%
toxicity100%
policy96%
[GUARDRAIL · BLOCKED]
output.policy.pii_redaction
Redacted 1 account number before write-back. Logged to audit with policy decision id.
02HOW IT WORKS

From data to governed agent in a day.

01

Connect data securely

Query your warehouse in place — connect over copy. Per-tenant isolation from the first call.

02

Build an agent

Pick a model through one gateway. Add tools, guardrails, and an eval set in minutes.

03

Ship governed

Every run is guardrailed, evaluated, and written to an immutable audit trail.

04

Bill by use

Per-seat platform fee plus metered usage. Watch spend live; upgrade when you grow.

[THE VISION]Agents today are the wedge — the ontology platform underneath is where decision-grade goes next.
See the platform vision →
03PRICING

Start free. Pay as you grow.

[FREE]
$0
1 agent · 1k runs / mo
Start free →
[TEAM]
$49
/ seat · usage metered
Start free →
[SCALE]
$199
/ seat · SSO · retention
Start free →
[ENTERPRISE]
Custom
VPC · SLA · region routing
Talk to sales →
Start freeCompare plans →