👤 I just want browser tools
You can ignore model names. Scroll to Part 2 or open the Toolbox and try a free tool.
Proof & timing · plain-language edition
Does the AI actually finish the job?
This page shows measured results — not marketing vibes. Part 1: can a small local AI finish a real file task when we guide it? Part 2: is one toolkit faster than bouncing across many free websites?
New to AI agents? Start here
You don’t need a PhD. In plain English:
- What is an “agent”?
- An AI that can call tools (resize an image, merge PDFs, make a QR code) instead of only chatting. Think of it as a junior assistant with buttons it can press.
- What is “Easy Mode”?
- A free helper that runs on your computer. It gives small local AIs a short checklist so they finish jobs more reliably — privacy stays local unless you opt into hosted tools.
- What do the big numbers mean?
- 0/20 = without guidance the AI never produced a correct compressed file in our test. 20/20 = with Easy Mode it succeeded every time. −78.6% = it also used far fewer “thinking” tokens (cheaper / faster for the model).
- What is Part 2 about?
- Everyday packs (social images, product photos, PDFs). We timed “many free websites” vs “Agent Media Tools in one place.” One toolkit won on speed in our automated tests.
🤖 I run a local AI (LM Studio, etc.)
Part 1 is for you. Then set up Easy Mode so small models finish tasks.
0 / 20
without Easy ModeAI never finished the file correctly
20 / 20
with Easy ModeAI finished every trial correctly
−78.6%
less model “thinking” workSame job, fewer tokens used
What this page is: honest measurements of (1) whether a local AI finishes a real file job, and (2) whether one toolkit beats multi-site busywork. What it is not: a ranking of which chat AI is “smarter,” or made-up “hours saved” claims.
Part 1 · Does the AI finish the job?Also called “verified execution” / Easy Mode benchmark · for local models
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.”
Image compress test (guided vs unguided)
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.
More tasks under the same rules
Next up may include exact resize, PDF merge, QR packs — still scoring real output files, not chat confidence.
Test details · image compressTechnical ID: IMG-COMPRESS-01 · same setup both sides
| 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 | A small local model: Qwen3.5 9B (compact install, often via LM Studio or similar on your PC). |
| 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. |
Results side by side
| 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 |
Keep expectations honest. This is one model, one image job, one controlled test. It shows that guidance helped a lot here. Other models, hardware, or tasks can differ — results are not a universal guarantee.
Animated story — same AI, same job (replay anytime)
Without Easy Mode
You: Compress this image under 80KB, keep 320×320
→ looks at the image…
→ describes the image…
→ browses tools… still not compressing
✗ Says “done” — file still too big (112 KB)
Failed · 0 of 20 trials
With Easy Mode
You: Compress this image under 80KB, keep 320×320
→ runs compress with a clear size goal
→ checks width & height…
→ checks file size: 61.2 KB ✓
✓ Real file accepted
Passed · 20 of 20 trials
How we score Part 1 (simple rules)
- Check the file, not the chat. A trial only counts if the output image passes size checks.
- Same starting line. Same AI, same settings, same test image — only guidance changes.
- No hidden cloud helper. Easy Mode does not secretly swap in a bigger online model to “fix” the score.
- We version the test. If we change Easy Mode or the image later, we label a new suite instead of rewriting history.
- Want the deep dive? Design article · Setup guide
Try the same idea at home
1. Install free Easy Mode
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).
2. Load a tool-capable small model
Models that support “tool calling” work best (for example many Qwen or Llama instruct builds). Closer match to our test = closer numbers.
3. Ask for a hard, clear job
Example: “Compress this image under 80,000 bytes without changing dimensions.” Require a real file, not just a yes.
4. Judge the file yourself
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.”
Part 2 · Is one toolkit faster?Also called “workflow ROI” · everyday packs, timed with a stopwatch-style script
In plain English: instead of opening four different free websites, can you finish the same pack in one place? We timed three common jobs. Agent Media Tools (one toolkit) was much faster in our automated comparison.
~88–98%faster in our automated testvs multi-website style path
1 websiteAgent Media Toolsvs about 4 different sites
~12.5ssaved doing all 3 packs onceAutomated timing — see note below
Picture the speed gap — social pack example
Many sites
6.7s
One toolkit
0.4s
Bars match our measured medians for the social pack (6.7s vs 0.4s). Longer bar = more time.
How to read Part 2 (important). “Many sites” is an optimistic stand-in: we loaded real free-tool websites and did the work with local tools — without CAPTCHAs, ads, or slow form clicking. Real humans tabbing around are usually slower. “One toolkit” is Agent Media Tools finishing the same checklist via its API. So the gap is real, and if anything it understates multi-site pain for people.
How we timed Part 2
- Same finish line first — we listed exact files that must exist before starting the clock.
- Same ingredients — same photos / PDFs for both paths.
- 5 runs each — we report the middle result (median), not a lucky best run.
- Many sites: open real free-tool pages + process files locally.
- One toolkit: Agent Media Tools requests that download real results.
- For nerds: harness
scripts/run-workflow-roi-bench.mjs· raw numbersdocs/workflow-roi-results.json.
Social content pack
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 | Typical time | Steps | Websites |
|---|---|---|---|
| Many free sites | 6.7s | 19 | 4 different places |
| Agent Media Tools | 0.4s | 12 | 1 place |
About 6.3s saved per pack (94.7%) in this automated test. Doing it 50 times/week ≈ 5.3 min of pure machine time; real multi-tab clicking is usually slower on the “many sites” side.
We checked: exact pixel sizes, QR created, short link + paste created. Does not include writing captions or posting to social apps.
Watch the pack build — one photo → ready assets
$ amt pack social --source hero.jpg
📷IG square1080×1080
𝕏X / Twitter1200×675
💼LinkedIn1200×627
📱Stories1080×1920
▣QR PNGbranded
🔗Short linkUTM ready
📋Team pasteone share
✓Done0.4s median
Playbook → · Resize → · QR →
Product image pack
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 | Typical time | Steps | Websites |
|---|---|---|---|
| Many free sites | 3.5s | 10 | 4 different places |
| Agent Media Tools | 0.4s | 9 | 1 place |
About 3.1s saved per product image (88.8%) in this automated test. 100 products/week ≈ 5.2 min of pure machine time.
We checked dimensions, WebP output, and the size budget. No photo retouching or AI art generation in this test.
Product pack ready
🛍️
listing.jpg1600×1600 · WebP + grid 800²
<250 KB
analyze → resize → convert → compress→0.4s median
Document intake pack
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 | Typical time | Steps | Websites |
|---|---|---|---|
| Many free sites | 3.2s | 11 | 4 different places |
| Agent Media Tools | 0.1s | 6 | 1 place |
About 3.1s saved per packet (97.8%) in this automated test. 100 packets/week ≈ 5.2 min of pure machine time.
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).
Watch the pipeline — three PDFs → one intake pack
A.pdf
+
B.pdf
+
C.pdf
→
merge
→
extract
→
tokens
→
paste ✓
✓ MARKER_A · MARKER_B · MARKER_C found · 0.1s median
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.
What should I do next?
Pick the path that matches you — no need to understand every acronym.
I want free browser tools
Open the Toolbox and try compress, resize, PDF, or QR — no agent required.
I run a local AI on my PC
Install free Easy Mode so small models finish jobs more often.
I want my agent on the web
Five-minute path: free API call → account → key → first authenticated request.
I hate juggling five SaaS tabs
See why one toolkit is the point — then try a workflow playbook.
FAQ
Is this ranking ChatGPT vs Claude vs Gemini?
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.
What does “0/20” and “20/20” mean?
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.
What is Easy Mode in one sentence?
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.
Why are Part 2 times only seconds?
Both sides of Part 2 are automated (scripts + page loads), so they finish fast. That still shows a big relative gap. Real humans clicking free websites are usually slower on the multi-site side — we deliberately kept that side optimistic so we don’t overclaim.
Did a big cloud model secretly do the Easy Mode work?
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.
Can I quote these numbers?
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.”
Related
Easy Mode setup
Install the free bridge and connect LM Studio, Open WebUI, or Hermes.
Design article
Why small models fail at tools and what the seven controls change.
First win
Free curl → browser tool → account → API key in about five minutes.
One toolkit vs glue
Why builders consolidate image, PDF, and utility vendors.
Ready to try something real?
New users: open the free Toolbox. Local AI users: install Easy Mode. Builders: grab a free API key in five minutes.