AI Check-In: Which Agents Are You Currently Using?

[NarrowBandFtw]

I don't want to be restricted to Ollama's models, they all seem to be quite puerile.

the latest versions of Qwen, Deepseek and even Gemma are easily as capable as Opus

 

[Hemps]

Promptcowboy - to create a decent prompt
claude - to create initial baseline
deepseek - once baseline has been created in Claude, copy and paste code into Deepseek, I find deepseek can easily continue without issues
chat.z.ai - backup at this point

 

[SauRoNZA]

Tools or Agents?

Because neither Claude nor Gemini have Agents as far as I’m aware.

 

[w1z4rd]

Gemini user here. I use it a lot for breaking down log files or creating bash scripts to help me manage servers. Especially when I inherit servers that was setup in 2012 gentoo or something like that and I have to manage a couple of thousand user accounts on that server.

 

[Herr der Verboten]

Sure, it can be wrong, even when you prime it properly. It's AI after all.
But it's still far less wrong than any of the others, who are so high that they could be mistaken for Deep Purple groupies.

idk, for the latter seems claude and gpt is more correct, however all of them will always go with what has been "the most correct" even if that is wrong. Ask grok (or any llm) to explain what the difference between tapioca flour and tapioca starch is - all of them will tell it's the same whereas it is not.

I mostly use grok as my google-bitch and image generation other than that gpt and cluade is just better.

 

[Herr der Verboten]

Tools or Agents?

Because neither Claude nor Gemini have Agents as far as I’m aware.

call it a ****(s) if you want

 

[Herr der Verboten]

It was the point I was getting to. What it is today is an ecosystem and it can be mixed to your heart's desire. AI, as it is known today, does take skill and experience to maximize.

I did lol a bit when I saw that GabeN once supported OpenAI. Knowing Valve's grey'ish stance on AI use. At least we know how they got their bots so well trained on dota.

Do the jesus take the wheel experiment with one of them, it was interesting to see how far claude can and will go if given no restrictions and full control. haha.

 

[Herr der Verboten]

What is that? Sounds like a microsoft thing.

I use Grok when I want a good argument.
View attachment 1905675

I wish you can remove their copilot from visual studio and its buttons...

 

[Nimz]

Gemini Pro (because Family sub and access to more features with a single sub e.g Antigravity, Nano Banana etc)

Claude Pro (Cowork mainly among other tools)

 

[Herr der Verboten]

Gemini user here. I use it a lot for breaking down log files or creating bash scripts to help me manage servers. Especially when I inherit servers that was setup in 2012 gentoo or something like that and I have to manage a couple of thousand user accounts on that server.

For legacy I do find this useful running claude cli to at least assist with an overview, how it works, what it does - even that I turn into a 3 part document for the next time. You are going to waste more time reading a while system end to end when the LLM can give you brief and you use that to go through it.

Obviously, buyer beware... as to anything the llm can or will say.

 

[RedViking]

I use NotebookLM to work through large documents. However it often makes up stuff. But it is nice to pick up on things to go check. Also it is affordable as I already have a Google sub.

Claude is ridiculously priced and it often runs out of credits or whatever they call it. It's useless most of the time. I wanted to use it to manage my Notion PKB but it can barely do much before it is exhausted.

In fact, I find using AI as a productivity tool is more exhausting than helpful. This world is screwed.

No need to use anything else.

 

[Herr der Verboten]

I use NotebookLM to work through large documents. However it often makes up stuff. But it is nice to pick up on things to go check. Also it is affordable as I already have a Google sub.

Claude is ridiculously priced and it often runs out of credits or whatever they call it. It's useless most of the time. I wanted to use it to manage my Notion PKB but it can barely do much before it is exhausted.

In fact, I find using AI as a productivity tool is more exhausting than helpful. This world is screwed.

No need to use anything else.

It is funny until it is not and you need to reel them in at times and even then, they get stuck in a loop. Only fix is to close and delete that chat windows I've found. However, this also happens because they choose and interject from their mostly used and popular answers. Which is telling why AI can go seriously fubar.

 

[semaphore]

the latest versions of Qwen, Deepseek and even Gemma are easily as capable as Opus

No they're not and if you believe that you are clueless.

 

[semaphore]

I use NotebookLM to work through large documents. However it often makes up stuff. But it is nice to pick up on things to go check. Also it is affordable as I already have a Google sub.

Claude is ridiculously priced and it often runs out of credits or whatever they call it. It's useless most of the time. I wanted to use it to manage my Notion PKB but it can barely do much before it is exhausted.

In fact, I find using AI as a productivity tool is more exhausting than helpful. This world is screwed.

No need to use anything else.

I'm on the high tier of OpenAI, ChatGPT Pro is basically unlimited, as is deep research. But you'll need to cough up 2-4k pm.

My stats:

Total tokens: 101,247,360,919

 

[NarrowBandFtw]

No they're not and if you believe that you are clueless.

yes they are, and if you don't know it you haven't kept up with the latest developments

 

[semaphore]

yes they are, and if you don't know it you haven't kept up with the latest developments

Lol, sure. If you say so.

deepseek-v4-pro 344.4M tokens

Yeah, I don't keep up to date. lol

 

[gregmcc]

Other: They all suck. Tired of them all sending me in a constant loop and then apologising.

 

[semaphore]

Other: They all suck. Tired of them all sending me in a constant loop and then apologising.

Your prompting is bad. That is easily resolved.

 

[semaphore]

Other: They all suck. Tired of them all sending me in a constant loop and then apologising.

You can use a variation of this

# XX  Spec Map
This file is the short agent table of contents. Keep it concise.

## First Read

1. `docs/superpowers/review/track-start-prompt.md` - track/chunk workflow contract.
2. `docs/adherence.md` - execution and evidence constraints.
3. `docs/review_criteria.md` - consensus review contract.

## Track Plan Index (2026-05-05)
All 12 implementation track plans are in `docs/superpowers/plans/`:
| Track | Plan file |
|---|---|
| track01 | `2026-05-01-track-01-xx-setup-plan.md` |

## Conversation Commands (Spec-First)
- `./agent start track TRACK [chunk CHUNK]`: resolve scope and report scope only.
- `start track TRACK chunk CHUNK`: equivalent (tool-conversation form) for the above.
- `start chunk CHUNK`: infer active track from current context when clear; otherwise ask for track.
- `confirm start`: execute only the confirmed chunk plan.
- `./agent review track TRACK CHUNK`: run chunk review protocol against monitor/task artifacts.
- `review track TRACK CHUNK`: equivalent (tool-conversation form) for the above.
- `./agent review-track-gate TRACK [CHUNK]`: verify track/chunk gate completion from the latest review cycle.
- `./agent preflight`: run `tools/agent/preflight.sh`.

### Scope Convention
Treat these commands as *documentation planning gates* until implementation work starts. This repo is currently in spec stage.
## Hard Rules
1. Keep this repo spec-first: do not claim implementation closure without evidence artifacts.
2. Use small, explicit artifacts with low abstraction overhead.
3. Keep track/chunk evidence synchronized across:
   - `docs/superpowers/plans/`
   - `docs/superpowers/tasks/`
   - `docs/superpowers/evidence/`
   - `docs/superpowers/implementation/`
4. Adherence and review criteria are mandatory inputs before closing any chunk.
5. Use relative file paths that match repo-local references only.
6. Do not revert unrelated work unless explicitly asked.
## Rust Rules
[1] Read Cargo.toml, workspace, edition, rust-version, features, lints, CI, src/lib.rs, tests, unsafe/FFI before editing.
[2] Preserve public API, feature behavior, edition, and MSRV unless explicitly asked to change them.
[3] Borrow by default at API boundaries; avoid unnecessary ownership, allocation, and clone().
[4] Use Option for absence, Result for failure, and avoid unwrap on caller-controlled input.
[5] Keep binaries thin and reusable logic in libraries.
[6] Do not widen pub visibility to make code compile.
[7] Async: do not block executor threads or hold locks across .await.
[8] Unsafe: keep narrow, document every block with SAFETY, and wrap in safe abstractions.
[9] FFI: isolate raw bindings, document ownership/lifetime/layout/unwind assumptions.
[10] Add docs and tests for new public behavior.
[11] Run or satisfy fmt, clippy, check/test/doc, dependency/security, package, and semver gates.
[12] Flag semver impact for public API changes.
## Canonical Policy
- Product scope and architecture: `docs/xxx.md`
- Current plan index: `docs/plans/`
- Execution conventions and commands: this file + `docs/superpowers/review/track-start-prompt.md`
- Schemas: `docs/spec/*.schema.json`
- Review governance: `docs/adherence.md` and `docs/review_criteria.md`
## Harness Commands
- `scripts/check-spec-harness.sh` - lightweight spec consistency and link checks.
- `./agent start TRACK [CHUNK]` -> `tools/agent/start_track.sh`.
- `./agent review TRACK CHUNK` -> `tools/agent/review_chunk.sh`.
- `./agent review-track-gate TRACK [CHUNK]` -> `tools/agent/check_track_gate.sh`.
- `./agent next-chunk TRACK` -> `tools/agent/next_chunk.sh`.
- `agent check-track-artifacts` -> `scripts/check-track-artifacts.sh`.
- `agent check-agent-tools` -> `scripts/check-agent-tools.sh`.
- `agent preflight` -> `tools/agent/preflight.sh`.
## Track Closure Gate
- Track/chunk completion requires a successful latest-review-cycle pass:
  - `PASS 3/3`
  - 3/3 reviewers
  - zero blocking findings
  - zero non-blocking findings
  - PASS verdict
- Do not move to the next chunk or next track on narrative progress alone; require the applicable latest review cycle to reach `PASS 3/3` first.
- Current track01 execution constraint: stay mac-first; keep Windows/Linux/headless jobs scaffold-only and deferred from `chunk00` closure until explicitly redirected.
- Use `tools/agent/check_track_gate.sh TRACK CHUNK`.
## Verification
Run this before marking a track chunk complete:
```bash
scripts/check-spec-harness.sh
```
Run full workflow check before closure:
```bash
tools/agent/preflight.sh
```

adherence

# Strict Adherence Contract (xxx Spec Harness)
Date established: 2026-05-01  
Scope: all active tracks/chunks unless explicitly overridden.
## Non-Negotiable Rules
1. No partial implementations.
2. No placeholders, TODO-backed behavior, or fake-green completion claims.
3. No narrowed review scope that omits required chunk files/tests/evidence.
4. No protocol drift from active track/spec artifacts.
5. No hidden behavior changes not reflected in task/plan/evidence artifacts.
6. Do not mark tracks/chunks done without evidence that supports every acceptance item.
7. Preserve artifact alignment between plan/task/monitor/implementation notes whenever either changes.
8. All command evidence must include command text and the relevant output summary.
## Authoritative Source Order
1. `xxxmd`
2. Active track plan
3. Active track task
4. Active monitor
5. `review_criteria.md`
## Completion Gate
1. Scope is executed exactly as committed in the confirmed start prompt.
2. Required docs/spec/test evidence exists in monitor and/or task artifacts.
3. Required commands are run and outputs are captured.
4. Review findings (if any) are captured, triaged, and resolved.
5. The latest review cycle satisfies the applicable criteria and has no unresolved blocking findings.
## Test/Evidence Standard
- Behavioral claims must be backed by executable evidence whenever possible.
- If a required command is unavailable, record the blocker and approval state explicitly.
## Review Integrity
- Do not claim work completed from assumptions or narrative-only updates.
- If evidence is found stale, add a remediation note and refresh it before chunk close.

review_criteria

# Review Criteria (xx)
Date established: 2026-05-01  
Applies to: consensus reviews for active tracks/chunks
## Consensus Contract
1. Exactly 3 review inputs are required for a fresh review cycle.
2. Reviewers must run in strict isolation and use independent context.
3. Reviewers must not delegate or run orchestration scripts.
4. Include this line verbatim in every reviewer prompt:
   `Hard constraint: do not call spawn_agent, do not delegate, and do not run reviewer orchestration scripts.`
5. If any launch is interrupted or violates rules 1-4, discard and rerun until exactly three valid reviewers complete.
6. Final sign-off requires all three reviewers to return a non-blocking verdict.
7. Track/chunk completion check is explicit and requires:
   - 3 valid reviewers.
   - `PASS 3/3` review cycle status.
   - zero blocking findings.
   - zero non-blocking findings.
## Required Reviewer Output
Each review cycle entry must include:
- verdict (`PASS` or `FAIL`)
- blocking findings first (with file references where possible)
- non-blocking findings
- explicit sign-off recommendation
## Consensus Gate
- Any blocking finding => `FAIL`.
- `PASS` only when zero blocking findings and criteria above are satisfied.
- Chunk closure requires:
  - latest cycle status `PASS 3/3`
  - zero blocking findings
  - zero non-blocking findings
- Any invalid cycle must be rerun after blocker(s) are fixed.

This has been refined over a few months, there are a lot of other files you need but you can kinda infer what the rest should be. This uses spec driven development with superpowers and strict gating and review panels

 

[SHL]

I use Grok when I need to. It's a dream, especially when I have to get involved with the kids homework...