See every LLM call
PXFuse records every reasoning step, every token and every cent your agent spends. langfuse SDK compatible β three lines of config to connect.
Supported Agent Types
Read https://zero.polardbx.com/pxfuse/SKILL.md and follow the instructions to set up observability for your LLM app with your PXFuse project.
This is what one agent call looks like in PXFuse
Three lines to connect
PXFuse speaks the langfuse protocol β swap three environment variables and you are done
LANGFUSE_BASEURL=https://pxfuse.example.com
LANGFUSE_HOST=https://pxfuse.example.com
LANGFUSE_PUBLIC_KEY=pk-lf-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx
LANGFUSE_SECRET_KEY=sk-lf-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxxSample values below. Claim a project and your real credentials appear here automatically.
My Projects
Manage your provisioned PXFuse projects
Capability Map
Trace Β· Measure Β· Evaluate Β· Govern β four layers converging on production quality
Tracing
TracingFull-path traceability
- Full-path call tracing
- Nested span hierarchy
- Session context linking
- Error and retry annotation
Metrics
MetricsCalls quantified as metrics
- Throughput, latency, error rate
- Token usage and cost accounting
- Model, project, user drill-down
- Custom metric ingestion
Evaluation
EvaluationOutput quality made measurable
- Human annotation and scoring
- LLM-as-judge scoring
- Badcase-driven datasets
- Cross-version regression
Governance
GovernanceChanges controlled and reversible
- Prompt version control
- Staged rollout and rollback
- Project-level data isolation
- Per-project key authorization
From connect to operate
Four steps that turn LLM app quality into a loop you can keep iterating on
Connect
Connect
Drop in the host and key pair β calls report automatically, no logic changes
Debug
Debug
Expand your agent's multi-step tool calls and see exactly where it stalled
Optimise
Optimise
Surface the slow, expensive calls, then go back and tune prompts and models
Operate
Operate
Sample, score, regress badcases β let the data decide the next revision