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
Get it right once.Run it with checks.
Start from a template, adjust it until it’s right, and save it as a task. Every run after that is checked against your standard.
Start from a task template
All templatesNothing fits? Chat it through
An 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 have to check yourself, and explain again next time, 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. | It becomes a suggested change to the task. Approve it, and later runs follow it. |
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
Every run, on record.
What passed, what changed, what it cost.
Checked against your standard
See which item failed, which needs your call, and why.
Cost in plain sight
Every run records the model, usage and estimated cost.
Once, or on a schedule
Run it when new material comes in, or set a schedule. Every run is checked the same way.
Weekly competitor brief
Every Monday at 09:00
- Task run #4Nov 23 passedConfig v3Estimated cost: $0.12
- Task run #3Oct 262 passed · 1 failedConfig v2Estimated cost: $0.10
- Task run #2Oct 193 passedConfig v2Estimated cost: $0.11
- Task run #1Oct 122 passed · 1 needs reviewConfig v1Estimated cost: $0.12
How it improves
You decide what changes. The next run shows whether it helped.
Failed checks, your feedback and your own requests become suggested changes. Each one you approve is a new version.
Run
Each run uses the task’s current version.
Check the result
Each item gets a verdict and evidence. You accept, ask for edits or reject.
Suggested change
Drafted from failed checks and your feedback, with every edit marked.
You approve
Nothing changes until you do. Any earlier version can be restored.
Next run: new version, same standard
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 it out in a chat is the same. What’s different is what happens next: the chat becomes a task with your standard saved in it, so later runs are checked item by item, with evidence and cost, instead of starting over.
Will it send emails or publish posts for me?
Templates that write emails or posts only draft them. 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 whenever new material comes in. Once it works the way you want, you can also put it on a schedule.
What do you keep redoing from scratch?
Make it a task. Start from a template, and every run gets checked.