workledger
Observability tells you what ran. workledger tells you what work happened.
This report turns raw traces into normalized observations, rolled work units, and explicit review-needed work. Policy and economics remain downstream views.
work_unit_count
2
total_direct_cost
0.084
total_blended_cost
0.0966
avg_compression_ratio
1.12
avg_confidence
0.0
review_burden
1
pending_review_count
1
total_source_spans
8
Dataset Context
| Dataset | Split | Adapter | Rows | Traces | Observations |
|---|---|---|---|---|---|
| kshitijthakkar/smoltrace-traces-20260130_053009 | train | smoltrace | 2 | 2 | 8 |
Raw Trace Excerpt
| Title | Trace | Steps | Excerpt | Source ref |
|---|---|---|---|---|
| Work through multi-step prompt | trace-smol-2 | 5 | Work through multi-step prompt -> Retrieve docs -> Run calculator -> Reason over docs -> Return answer | hf://kshitijthakkar/smoltrace-traces-20260130_053009/train/1#span-1 |
| Solve benchmark prompt | trace-smol-1 | 3 | Solve benchmark prompt -> Search background facts -> Draft final answer | hf://kshitijthakkar/smoltrace-traces-20260130_053009/train/0#span-1 |
Normalized Observations
| Trace | Span | Kind | Name | Source ref |
|---|---|---|---|---|
| trace-smol-2 | root-2 | agent | Work through multi-step prompt | hf://kshitijthakkar/smoltrace-traces-20260130_053009/train/1#span-1 |
| trace-smol-2 | retrieve-2 | retriever | Retrieve docs | hf://kshitijthakkar/smoltrace-traces-20260130_053009/train/1#span-2 |
| trace-smol-2 | tool-2 | tool | Run calculator | hf://kshitijthakkar/smoltrace-traces-20260130_053009/train/1#span-3 |
| trace-smol-2 | llm-2a | llm | Reason over docs | hf://kshitijthakkar/smoltrace-traces-20260130_053009/train/1#span-4 |
| trace-smol-2 | llm-2b | llm | Return answer | hf://kshitijthakkar/smoltrace-traces-20260130_053009/train/1#span-5 |
| trace-smol-1 | root-1 | agent | Solve benchmark prompt | hf://kshitijthakkar/smoltrace-traces-20260130_053009/train/0#span-1 |
| trace-smol-1 | tool-1 | tool | Search background facts | hf://kshitijthakkar/smoltrace-traces-20260130_053009/train/0#span-2 |
| trace-smol-1 | llm-1 | llm | Draft final answer | hf://kshitijthakkar/smoltrace-traces-20260130_053009/train/0#span-3 |
Rolled Work Units
| Title | Kind | Review | Trust | Evidence | Spans | Total cost |
|---|---|---|---|---|---|---|
| Work through multi-step prompt | augmented_ai_work | queued | unreviewed | 6 | 5 | $0.0644 |
| Solve benchmark prompt | augmented_ai_work | unreviewed | unreviewed | 4 | 3 | $0.0322 |
Review-Needed Work
| Title | Kind | Review | Reason | Spans | Evidence |
|---|---|---|---|---|---|
| Work through multi-step prompt | augmented_ai_work | queued | queued during trace-to-work rollup | 5 | 6 |
Cost by Policy Outcome
| Policy outcome | Blended cost | Work units |
|---|---|---|
| No policy outcome totals available | ||
Pending Review Queue
| Title | Category | Outcome | Cost | Confidence | Spans | Compression | Competing |
|---|---|---|---|---|---|---|---|
| No pending review items | |||||||
Compression Proof Point
Work through multi-step prompt condensed 5 source spans into a 1.25x business work signal.
Top Ambiguous Items
| Title | Category | Confidence | Gap |
|---|---|---|---|
| No ambiguous items | |||
Low-Trust High-Cost Outputs
| Title | Category | Cost | Trust |
|---|---|---|---|
| No low-trust high-cost outputs | |||