Every draft
Edit to your rules
Revise a draft to your rules and the latest feedback. Your facts stay as they are.
Checks
- Every rule and piece of feedback is applied
- Nothing added to your facts
- Ends with what needs your confirmation
Chat it through.Put it to work.
Get a piece of work right once in a chat. Save it, and every later run follows your corrections and is checked against your standard.
New work? Chat it through
Familiar work? Use a template
All templatesAn example in three parts. In a chat, someone asks for a brief on what three competitors shipped, then corrects it once: only the last 7 days, with an official source for every item. They save the chat as a task; AI turns the conversation into requirements that include the correction, with three suggested checks. The task's first run comes back with a check report: two checks pass, and one needs review because Atlas’s price change only appears in a forum post. The report shows the evidence behind each verdict, the run’s usage and estimated cost, what the checks cost, and leaves the decision to accept, edit or reject the result to you. Then a suggestion drafted automatically from that run tightens the requirement: price changes need an official pricing page. Once applied, the next run passes all three checks.
Example. Names, results and costs are illustrative.
What’s different
Other AI chats end with an answer. ConsoleX starts there.
An answer you still have to check yourself, and redo from scratch every week, isn’t finished work.
| Chat assistant | ConsoleX | |
|---|---|---|
| Next time | Paste the prompt again and repeat last time’s corrections. | Your corrections are already in the task. Bring new material and run it. |
| Is it good enough? | You read it line by line and check it yourself. | Checked item by item against your standard, with evidence for every verdict. |
| What it can’t verify | Mixed in with everything else, for you to spot. | Listed separately for your call, never quietly passed. |
| When it misses | You work out what to change and rewrite the prompt yourself. | The miss becomes a suggested fix, drafted automatically if you like. Approve it and the next run uses it. |
| Every week | Start a new chat and do it all again. | Runs on a schedule. Every run is kept with its result, checks and cost. |
Start with the work you already repeat.
Each template comes with its checks. Change anything to fit how you work.
Every new set of notes
Deliverable from your materials
Turn notes, transcripts or documents into a recap, brief or proposal, using only what they say.
Checks
- Everything comes from your materials
- Fits the reader and the brief
- Ends with what needs your confirmation
Every new piece
Content repurposing
Turn one article, video or episode into a post for each of your channels.
Checks
- Nothing beyond the source
- Every channel gets its own version
- Ends with what needs your confirmation
Every month
Client report
SEO and AI-visibility numbers for a client’s site, what changed, and next steps.
Checks
- Numbers come from this run’s data
- Next steps follow from the findings
- Ends with what needs your confirmation
It keeps running. Quality and cost stay in your hands.
Every run leaves a record: what passed, what changed and what it cost.
Quality you control
Every run is checked against your standard, and you see which item failed, which needs your call, and why.
Every miss becomes a fix
A failed or uncertain check turns into a suggested change to the task, drafted automatically if you turn that on. You see the change first; it applies only when you approve it, and every version can be restored.
Cost in plain sight
Every run records the model, usage and estimated cost, so you can see what each result took, run by run.
Steady over the long run
It runs on its schedule and keeps every run with its result, checks and cost, so you can see at a glance whether quality and cost are holding steady.
Weekly competitor brief
Every Monday at 09:00
- Task run #4Nov 23 passedConfig v3Estimated cost: $0.12
Suggested automatically after run #3 and approved by you: link every update to the official changelog. Runs from #4 use Config v3.
Task run #3Oct 262 passed · 1 failedLumen: no source for the updateConfig v2Estimated cost: $0.10- Task run #2Oct 193 passedConfig v2Estimated cost: $0.11
Suggested automatically after run #1 and approved by you: price changes need an official pricing page. Runs from #2 use Config v2.
Task run #1Oct 122 passed · 1 needs reviewAtlas: only a forum postConfig v1Estimated cost: $0.12
Before you start
Questions people ask first.
Is ConsoleX for me?
It’s built for people who deliver the same kind of work again and again and answer for it themselves: freelancers, creators, consultants and founders running a one-person business. If you only ask AI the occasional question, a chat assistant is enough.
How is this different from ChatGPT or Claude?
Working something out in a chat is the same. What happens next is different: the conversation becomes a task with your standard saved in it, so the next run is checked item by item, with the evidence and its cost, instead of starting over in a new chat.
Will it send emails or publish posts for me?
The outreach and repurposing templates only draft. You review the result and send or publish it yourself. ConsoleX can email you when a run finishes.
Will it change my task on its own?
No. Suggested changes, including ones drafted automatically after a failed check, take effect only after you review and approve them, and every version of the task can be restored.
Can AI really check AI?
Rules that can be verified directly, such as required sections, links or banned words, are checked without a model. Where judgment is needed, the verdict has to cite evidence. If the evidence isn’t there, the item is marked for review rather than passed. You make the final decision.
Does “passed” mean the result is correct?
No. A check compares the result with your standard. It doesn’t guarantee that every fact is correct, and you can overrule any verdict.
Can it check Word, Excel or PDF files?
Not yet. Checks read the final response and the record of what the tools returned; they don’t open generated files. You can download files and review them yourself.
What does the cost figure include?
Each run shows its usage and an estimated cost, with checks estimated separately. Estimates can be incomplete, don’t include charges from external services, and are not a spending cap.
Can a task run once, or on a schedule?
Both. Run it once when you need it. Once a task works the way you want, put it on a schedule.
What did you figure out in chat this week?
Save it as a task, and let it keep getting done.