Traces & replay
Every step, every token, every reason.
- Nested spans for LLM calls, tools, retrieval and sub-agents
- Inputs, outputs and the model's reasoning, with PII masked
- Replay a run from any step with a new prompt or model
Agent operations
Fernline is the control room for AI agents in production: see every step and token, route risky tool calls to a human, and keep LLM spend inside budget.
SOC 2 Type II · GDPR · EU or US data residency
Example Fernline console: runs, success rate, cost by model, the approval queue, a run trace, budget, failing agents, alerts and live activity.
Trusted by 1,200+ AI teams shipping agents to production
The problem
Agents fail differently from APIs. They don't throw, they improvise. You need to see what they did, step by step, and stop the risky parts before they happen.
The run says “completed”. The agent looped on a tool, gave up and apologised to the customer. Nobody noticed for a week.
1 in 9 “successful” runs has a hidden error
A retry loop or a 200k-token context turns a $0.05 run into a $4 run. You find out on the invoice.
Spend spikes are found 11 days late on average
Refunds, emails to customers, SQL on production. Agents act with your credentials, and nobody signs off.
63% of teams have no approval step for writes
How it works
LLM calls, tool calls, retrievals and sub-agents on one timeline, with tokens, cost and latency per span.
Likely cause: the help-center MCP server returns an empty page instead of an error.
Suggested fix
Add a max-calls guard of 5 for search_kb and treat empty pages as “no results”.
Errors are grouped by cause, with the failing span, similar runs and the prompt version that introduced it.
SDR Outreach
Policy: Bulk email
Send email to 402 contacts
send_email({"sequence":"Q4 expansion: ops leaders", "recipients":402, "from":"[email protected]", "send_at":"now"})
“I found 402 ops leaders matching the ICP and drafted a 3-step sequence. Sending now keeps us inside this week's quota.”
Policies pause the run before a refund, a bulk email or a SQL write. Approve, reject or edit the arguments.
Month to date
$74.00
of $260.00 · forecast $273.00
Forecast is $13 over. The agent pauses when it hits the limit.
Budgets per agent, team or workspace. Alert at 80%, pause at the hard limit, forecast the month.
Traces & replay
Approval queue
Issue refund $420 to customer #8812
Refund Assistant
Publish status update for incident #331
Incident Summarizer
Run SQL DELETE on staging.sessions_2024
Data Cleanup Bot
Send email to 402 contacts
SDR Outreach
Tool-call log
| Time | Tool | Agent | Status | Latency |
|---|---|---|---|---|
| 09:22:48 | post_status | Incident Summarizer | Held | — |
| 09:22:36 | summarize_timeline | Incident Summarizer | OK | 5.4s |
| 09:22:31 | fetch_alerts | Incident Summarizer | OK | 5.1s |
| 09:16:58 | query_warehouse | Data Cleanup Bot | OK | 4.9s |
| 09:10:00 | lookup_order | Refund Assistant | OK | 2.5s |
| 07:14:48 | search_kb | Support Triage | Error | 2.9s |
Cost & budgets
LLM spend, last 30 days
$594.17
And so much more
Turn real runs into test cases and score every prompt version before it ships.
Loops, cost spikes, error rates and SLA breaches, routed to the right channel.
Mask emails, cards and custom patterns before payloads leave your network.
Approvers, developers and viewers. Approval rights per policy, not per workspace.
Every prompt change is a version with a diff, an owner and its own metrics.
Python and TypeScript SDKs, or send OTel spans from any framework you already use.
Use cases
Agents
Example policy
issue_refund where amount > $250 → Support Lead42%
of tickets resolved with no human touch
Sample result
OpenAI, Anthropic, LangGraph, Slack, Datadog, and anything else your agents run on.
Explore integrationsControl cost
Hard limits per agent pause runs before the bill surprises you. Forecasts tell you on day 5 what day 31 will look like.
Customers
“Budgets with a hard stop were the only way finance would let us put agents on the expensive models. Spend is down 30% anyway.”
Security
Audited annually. Report available under NDA from the trust center.
Choose US or EU at signup. Enterprise can keep payloads in its own VPC.
SAML and OIDC with any identity provider, with automatic provisioning.
Every approval, policy change and API key action, exportable to your SIEM.
Pricing
Every plan includes traces, approvals and cost tracking. Upgrade for volume, retention and controls.
For one team getting its first agents into production.
Includes
For teams running agents that touch money, data or customers.
Everything in Starter, plus
For organisations with security, scale and compliance needs.
Everything in Team, plus
FAQ
Can't find what you're looking for? Write to us and a human answers within a day.
Free for your first 100k spans. Set up in ten minutes, see your first trace in two.
No card needed · SOC 2 Type II · Cancel anytime