How does the tool decide automation potential?

It scores each step by work type — repetitive, rule-based, and text-heavy tasks score high, while judgement-heavy or physical tasks score low — and weights that by how often the step runs. A high-potential step that runs daily rises above a high-potential step that runs once a quarter.

How is time saved estimated?

The planner multiplies each step's duration by its monthly frequency to get total monthly minutes, then applies a realistic automation factor for its type (for example, AI rarely removes 100% of a task, so high-potential steps are credited with a large but partial reduction). The result is an order-of-magnitude guide, not a guarantee.

What counts as a high-potential step?

Drafting text, classifying or routing items, summarising, extracting data from documents, and answering repetitive questions all automate well with current AI. Steps needing physical action, legal sign-off, or genuine human judgement score low and are flagged to keep a human in the loop.

Should I automate the highest-potential step first?

Sort by monthly time saved, not raw potential. A medium-potential step that consumes ten hours a month often beats a high-potential step that takes five minutes once a week. The planner surfaces this by combining potential with volume.

Is my workflow data stored?

No. Everything runs in your browser and nothing is uploaded. Close the tab and the data is gone, so it is safe to map sensitive internal processes.

AI Workflow Planner — Gera Tools

An AI workflow planner turns the vague question “where should we use AI?” into a ranked, evidence-based shortlist. Most teams either over-automate a flashy step that barely runs or ignore a tedious daily task that quietly eats hours. By laying out each step of a process with its duration, frequency, and type, this planner scores automation potential and estimates the monthly time each automation would return — so you spend your first AI project on the step with the best payoff.

How it works

You add each step in your process and tag it with a duration (minutes per run), a frequency (runs per month), and a type — drafting, classifying, summarising, data entry, judgement, or physical. The planner assigns an automation-potential score from the type: text and rule-based work scores high, judgement and physical work scores low. It then multiplies duration by frequency to find total monthly minutes spent, applies a realistic partial-automation factor for high and medium steps, and reports estimated minutes saved per month per step. Sorting by that figure reveals the highest-ROI place to start. All computation happens locally in your browser.

Tips and examples

Break processes into granular steps — “handle support” is too coarse to score, but “triage incoming ticket”, “draft first reply”, and “escalate edge cases” each get a clear, useful score. Be honest about frequency; a step that feels painful but runs rarely is usually a poor first project. Treat the time-saved numbers as directional and validate the top one or two with a real pilot before committing. Keep judgement-heavy steps human-in-the-loop even when adjacent steps automate — the planner deliberately flags these low so you do not hand a final decision to a model that should only be assisting.