Observability
for the agents
you ship.

Cost attribution, live monitoring, and quality scoring — built for the teams running them in production.

Founding cohort First 50 customers lock in founding pricing for life.

30 seconds No card Build updates only
live · agent activity streaming
this week ↗ 12.4%
£4,870
spent
125,403
runs
94.2%
success
top spenders cost / runs
› content-writer £2,189
› research-agent £1,474
› support-triage £685
› email-classifier £413
001 the three blind spots when running agents
01

The silent failure

Our support-triage agent quietly broke for 11 days. We found out from a customer.

Heartbeat monitoring with expected schedules. Get paged in seconds when a scheduled agent goes silent, with full context on what was supposed to run and what the last successful run produced.

02

The mystery bill

Our token bill jumped from £2,400 to £8,900 last month. Three days to figure out which agent.

Per-agent, per-customer, per-feature cost attribution. Spend alerts the moment any agent breaks its own baseline. Cost-per-successful-run as the metric finance can build budgets around.

03

The quality drift

We shipped a prompt change. Output quality fell 22%. Nobody noticed for two weeks.

Define what good looks like once: a rubric, a JSON schema, an LLM-as-judge prompt. Every run gets scored. Drift surfaces in your dashboard before it surfaces in your support inbox.

002 three subsystems, one platform

Every team running agents in production needs the same three things working together. Most stitch them together from a pile of separate tools. We ship them as one platform.

[A]

Spend

Stop finding out about the bill at month-end.

  • Per-agent, per-customer, per-feature cost rollups — see exactly which customer is burning tokens
  • Cost-per-successful-run as your headline metric
  • Spend alerts when any agent breaks its own baseline
  • Token-by-token attribution across Anthropic, OpenAI, Bedrock, Gemini
  • Monthly invoice reconciliation reports for your finance team
[B]

Pulse

Find the dead agent before your customer does.

  • Heartbeat monitoring with expected schedules
  • Run-level traces with tool calls, latency, and outputs — replay any run to see what your agent actually did
  • Failure clustering: 12 broken runs become one issue
  • Alerts to Slack, PagerDuty, Microsoft Teams, Linear, or webhook
  • Multi-agent trace propagation — follow the trace when one agent kicks off another, no lost context
[C]

Verify

Catch the 22% quality drop before users churn.

  • Schema and heuristic checks at zero cost on every run
  • LLM-as-judge with rubrics you write in plain English
  • Bring your own provider key — judge calls billed by Anthropic, OpenAI, or whoever you pick
  • You set the sample rate, you control the spend
  • Drift detection and weekly stakeholder reports
003 pricing

Three tiers. No per-seat. No per-span tax.

Starter
£99/mo

For one team running a handful of agents.

  • 1 project
  • 10 agents
  • 100k events / month
  • 30-day retention
  • Email + Slack alerts
  • Schema + heuristic scoring
Join Waitlist
Business
£499/mo

For larger teams with multiple agent fleets.

  • Unlimited projects
  • 100 agents
  • 10M events / month
  • 1-year retention
  • SSO / SAML
  • Audit log
  • LLM-as-judge with custom evals — bring your own key
  • Priority support
Join Waitlist
Running more than 100 agents, or need SOC2 or volume pricing?  Custom enterprise tiers are available.
004 works with what you already use
[A]

Auto-instrumented LLM SDKs

Two lines in your code and every Anthropic, OpenAI, Bedrock, Mistral, Gemini, or Cohere call is captured: tokens, cost, latency, tool use, errors. No manual tracing.

[B]

Native framework integrations

First-class hooks for LangChain, LlamaIndex, Vercel AI, Pydantic AI, CrewAI, and the OpenAI Agents SDK. Trace agent loops, chains, and handoffs without custom plumbing.

[C]

Webhook for everything else

One authenticated HTTP endpoint works from cron, n8n, Make, Zapier, GitHub Actions, Claude Routines, or any shell script. If your agent can curl, it's monitored.

[A] LLM providers auto-instrumented
Anthropic Claude calls captured
OpenAI GPT calls captured
Gemini Gemini calls captured
AWS Bedrock Bedrock calls captured
Mistral Mistral calls captured
Cohere Cohere calls captured
[B] frameworks & sdks native integration
LangChain Chain-level traces
LlamaIndex Pipeline traces
Vercel AI streamText hooks
Pydantic AI agent.run() hooks
CrewAI Crew-level tracking
Agents SDK Agent loop tracking
[C] runtimes & schedulers webhook ping
Claude Routines Webhook on each fire
GitHub Actions Workflow webhook
n8n HTTP node webhook
Make HTTP module webhook
Zapier Webhook action
cron / shell curl in your shell
Anything else?  If your agent can curl, it works. Custom integrations via plain HTTP.
005 how it works
01

Your agent runs

Python, TypeScript, cron, n8n, Claude Routine, anything. Two lines of code or one HTTP request.

02

AgentPing captures

Tokens, cost, latency, tool calls, outputs. Captured asynchronously and never blocks your agent — if our service is down, yours keeps running.

03

You see everything

Live dashboard, drift alerts to Slack or PagerDuty, weekly reports for your team and finance.

Two lines for full instrumentation. One URL for everything else.

Native SDKs for Python, TypeScript, Go, Ruby, and PHP auto-capture every Anthropic, OpenAI, Bedrock, or Gemini call your agents make, with tokens, cost, latency, tool use, and errors.

For agents you can't host an SDK in, a single authenticated webhook works from cron, n8n, GitHub Actions, Claude Routines, or anything that can speak HTTP.

pip install agentping python 3.9+
import agentping

agentping.init("daily-summary")

# auto-captures every llm call
# anthropic · openai · bedrock · gemini
npm install agentping typescript / node 18+
import { AgentPing } from "agentping";

AgentPing.init({ agent: "daily-summary" });

// works with @anthropic-ai/sdk, openai,
// vercel ai sdk · node, bun, deno
go get github.com/agentping/agentping-go go 1.21+
import "github.com/agentping/agentping-go"

agentping.Init("daily-summary")

// wraps anthropic-sdk-go, go-openai
// context-aware, goroutine-safe
gem install agentping ruby 3.0+
require "agentping"

AgentPing.init("daily-summary")

# wraps anthropic-ruby, ruby-openai
# works with sidekiq, rails jobs, rake
composer require agentping/agentping php 8.1+ / laravel
use AgentPing\AgentPing;

AgentPing::init('daily-summary');

// auto-discovered service provider
// hooks scheduled commands + queued jobs
no install · no sdk bash / curl
# a single request, that's it
curl https://api.agentping.io/p/your-agent-id

# report status, duration, cost as params
curl "https://api.agentping.io/p/your-agent-id?status=ok&cost=0.012"
006 who is this designed for

Built for teams moving fast and deploying agents.

If one of these reads like you, you're in the right place.

[I]

The product engineer

"We ship AI features inside our product — a support agent, a triage classifier, a summariser. The token bill needs keeping an eye on."

  • 1 product, 5–20 agents in production
  • Customer-facing AI features
  • Need to know which customer is burning what
  • One-team eng, no dedicated SRE yet

Most start on Team.

[II]

The AI engineering lead

"We run several agents in production. They call other agents. One goes silent and we find out from a Zendesk ticket. We need traces, heartbeats, and an alert path on-call respects."

  • Multi-team, 30–100 agents across products
  • Multi-step loops, agent-to-agent handoffs
  • On-call rotation that needs real signals
  • Audit log + SSO start to matter

Most start on Business.

[III]

The shipping founder

"I shipped one critical agent into the product six weeks ago. I check the logs every morning before opening Linear. I need to sleep through the night."

  • Solo or small team, 1–5 agents
  • One agent does most of the work
  • Cost discipline before quality discipline
  • Slack alert is enough; no PagerDuty yet

Most start on Starter.

007 questions you'll have

When does this launch?

Closed beta is running today. General availability is planned for the second half of 2026. Get on the waitlist to be invited as cohorts open.

Will it slow my agents down?

No. The SDK never blocks your agent. Telemetry runs on a separate thread with a hard 2-second timeout, a bounded local queue, and graceful degradation when our service is unreachable. If we go down, your agents run as if we weren't installed.

What's the deployment model?

Hosted SaaS at launch. EU and US regions available.

Can I export my data?

Yes. Full event export to JSON or Parquet. API access on every tier. We don't lock your data in.

What about SOC2, GDPR, data residency?

GDPR-compliant from day one. SOC2 Type II within 12 months of launch. EU region available now; project-level setting for redacting prompt and output bodies if you'd rather not send content at all.

008 founding cohort

Lock in founding pricing before the cohort closes.

Join the founding 50 and get lifetime founding rates (£79 / £199 / £399), a direct line to me on Slack during onboarding, and a real say in what ships next. Once the 50th seat is taken, founding pricing closes for good. Standard pricing applies after.

Lifetime founding pricing Lock in your tier rate forever, regardless of where standard pricing lands.
30-minute onboarding call Walk through your agent setup with me, get the SDK wired in cleanly.
Roadmap input Founding members vote on what ships next. The next three features will come from this cohort.

No spam. Build updates only. Unsubscribe whenever.

You're on the list