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 with a template or work it out in a chat, then save it as a reusable task. Check each run against your standards, and use what you learn to improve the task over time.
Start from a task template
All templatesNothing fits? Chat it through
An example in four 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, and what the checks cost. The owner reviews the result, marks it Fail and gives the reason: the price change has no official source. 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
Profiles
Set up each client and product once.
A profile keeps what your work is for: a client’s voice, words and facts, or a product’s facts and the claims you can back up. Tasks that name it follow it on every run, and their checks read it.
Daniel Kim
- About the client
- Founder of a two-person brand studio. Read by agency owners on LinkedIn.
- Voice and notes
- Short sentences, first person. Under 200 words, no emoji.
- Words and phrases to avoid
- game-changersynergy10x
- Facts and stories you can use
- Rebranded 40 neighborhood cafés since 2019approved post, 12 Sep
- Rules from client notes
- No prices in posts.From run #4
Draft it from what you have
Give AI a client’s approved posts or style guide, or your product’s web page or brief. It drafts the profile; you check it and save it.
Every task follows it
Choose the profile in a task. Each run records the version it was written with, and its checks read that same version.
Change it once
Update a preference in the profile, and every task that uses it follows it from the next run. Rules a run suggests from client notes go in only when you add them.
Every run, on record.
What passed, what you decided, what changed, what it cost.
Checked against your standard
See which item failed, which needs your call, and why. A run you review counts as your Pass or Fail.
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 2Automatic check: Pass3 passedConfig v3Estimated cost: $0.12
- Task run #3Oct 26Automatic check: Fail2 passed · 1 failedConfig v2Estimated cost: $0.10
- Task run #2Oct 19Automatic check: Pass3 passedConfig v2Estimated cost: $0.11
- Task run #1Oct 12Human review: Fail2 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 reviews 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. Review the run yourself when you want: Pass or Fail, with your reason.
Suggested change
Drafted from failed checks and the reasons you gave, 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.
Do I need a profile?
No. Most tasks work without one. Templates that write for a client or about your product ask you to choose one, and you can draft it with AI from a document or web page without leaving the task.
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. You can review any run yourself and mark it Pass or Fail; your review is what counts in pass rates.
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.