I just want browser tools
You can ignore model names. Scroll to Part 2 or open the Toolbox and try a free tool.
Measured evidence · two distinct tracks
Part 1 measures whether a small local model produces a file that passes objective checks. Part 2 separately measures orchestration overhead in a synthetic multi-tool path. Neither is a general AI leaderboard or a human productivity study.
Read the tracks separately. Track 1 is a model-execution experiment. Track 2 is a synthetic software-path benchmark. The percentages in Track 2 describe elapsed machine time only; they do not measure employee time, usability, or business ROI.
In plain English: we gave the same small local AI the same “compress this image” task 20 times. Without guidance it never produced a correct file. With Easy Mode it succeeded every time. Success means we checked the actual file — not just that the AI said “done.”
Make a fixed test image smaller than 80,000 bytes without changing its size (320×320 pixels). The AI only “wins” if the output file passes those checks.
Next up may include exact resize, PDF merge, QR packs — still scoring real output files, not chat confidence.
| What we fixed | What that means |
|---|---|
| The job | Compress a fixed test image below 80,000 bytes without changing its pixel size (must stay 320×320). |
| The test file | Same image file every time for fair comparison. |
| The AI model | Qwen3.5 9B Q4_K_M, served locally through an OpenAI-compatible LM Studio endpoint. |
| What stayed the same | Same model, settings, file, goal, and 20 tries each side — only the “guidance layer” changed. |
| Without Easy Mode (“raw”) | The AI sees a big menu of tools and has to figure everything out alone. |
| With Easy Mode (“guided”) | A short checklist: remember the goal, try again safely, and check the file before claiming success. |
| How we score a win | The finished file must exist, stay 320×320, and be under 80 KB. The AI saying “done” is not enough. |
| How unguided usually failed | It inspected or described the image instead of compressing — then claimed success while the file was still too big. |
| How the AI worked | Jobs finished correctly | Thinking cost (tokens) | What helped it |
|---|---|---|---|
| Without Easy Mode Big tool menu, no checklist |
0 / 20 | 21,738 average | Tools only — no extra guidance |
| With Easy Mode Short checklist + file checks |
20 / 20 | 4,653 average (−78.6%) | Goal memory, safe retries, output verification |
Download the local bridge for Windows, macOS, or Linux. Point it at LM Studio, Ollama, or another local AI server on your machine (or a trusted home network address).
Models that support “tool calling” work best (for example many Qwen or Llama instruct builds). Closer match to our test = closer numbers.
Example: “Compress this image under 80,000 bytes without changing dimensions.” Require a real file, not just a yes.
Check width, height, and file size. If the AI says “done” but the file fails, count it as a fail — same as we do.
# Optional: power users — start the free local bridge export AMT_LLM_UPSTREAM_URL=http://127.0.0.1:1234/v1 # or your LM Studio address export AMT_EASY_MODE=true npm start # Then in your chat UI: “Compress /path/to/image.png under 80000 bytes without changing dimensions.”
Question tested: how much elapsed machine time does a unified API path remove compared with a constructed multi-tool path? The baseline combines measured page-load latency from real tool sites with equivalent local CLI processing. It does not upload files, fill forms, or complete work through those third-party interfaces.
Bars match our measured medians for the social pack (6.7s vs 0.4s). Longer bar = more time.
scripts/run-workflow-roi-bench.mjs · raw numbers docs/workflow-roi-results.json.What you get: one photo turned into Instagram, X/Twitter, LinkedIn, and Stories sizes, plus a QR code, short tracking link, and a shareable notes paste.
| Path | Median time | Steps | Origins |
|---|---|---|---|
| Synthetic multi-tool | 6.7s | 19 | 4 origins |
| AMT REST API | 0.4s | 12 | 1 origin |
94.7% less elapsed machine time in this synthetic test. This is an API-path result, not a claim about minutes of human labor saved.
We checked: exact pixel sizes, QR created, short link + paste created. Does not include writing captions or posting to social apps.
Playbook → · Resize → · QR →
What you get: one product photo → small grid size (800×800), large hero (1600×1600), modern WebP version, listing file under 250 KB, plus a short size note.
| Path | Median time | Steps | Origins |
|---|---|---|---|
| Synthetic multi-tool | 3.5s | 10 | 4 origins |
| AMT REST API | 0.4s | 9 | 1 origin |
88.8% less elapsed machine time in this synthetic test. No human-time extrapolation is made.
We checked dimensions, WebP output, and the size budget. No photo retouching or AI art generation in this test.
What you get: three PDFs combined into one, text pulled out, a rough “how big is this for an AI?” token count, and a short intake note.
| Path | Median time | Steps | Origins |
|---|---|---|---|
| Synthetic multi-tool | 3.2s | 11 | 4 origins |
| AMT REST API | 0.1s | 6 | 1 origin |
97.8% less elapsed machine time in this synthetic test. No human-time extrapolation is made.
We checked the merge and that marker text from each PDF showed up. This test uses PDFs that already contain text (not scanned photos of paper).
Power users / reproduce Part 2: node scripts/run-workflow-roi-bench.mjs with your API key · full protocol in docs/workflow-roi-benchmark-specs.md.
Pick the path that matches you — no need to understand every acronym.
Open the Toolbox and try compress, resize, PDF, or QR — no agent required.
Install free Easy Mode so small models finish jobs more often.
Five-minute path: free API call → account → key → first authenticated request.
See why one toolkit is the point — then try a workflow playbook.
No. We are not ranking chat AIs. Part 1 tests whether a small local model finishes a file job with vs without Easy Mode. Part 2 times multi-site busywork vs one toolkit.
We ran the same compress job 20 times. Without Easy Mode: zero correct files. With Easy Mode: twenty correct files. We checked the actual images, not the chat messages.
A free local helper that gives small on-device AIs a short checklist so they finish tools more reliably — without sending your files to a cloud model unless you choose to.
No. It measures a synthetic baseline of page-load latency plus local CLI work against an authenticated AMT API path. It is useful for understanding orchestration overhead, not for claiming employee time saved.
No. The same local Qwen model ran both sides. Easy Mode adds structure around it; it does not swap in a larger online model for the published score.
Yes — link this page, mention the date of the test, and include the caveats (one model / one task for Part 1; automated multi-site lower bound for Part 2). Prefer the full story over only “20/20.”
Install the free bridge and connect LM Studio, Open WebUI, or Hermes.
Why small models fail at tools and what the seven controls change.
Free curl → browser tool → account → API key in about five minutes.
Why builders consolidate image, PDF, and utility vendors.
New users: open the free Toolbox. Local AI users: install Easy Mode. Builders: grab a free API key in five minutes.