Fill your model with a browser-capable AI agent

Have a Tessly account and a separate practice model ready. Sign in yourself using the Open Tessly link. Prepare your currency, forecast start date, revenue, costs, team and cash. This walkthrough uses the SaaS B2B template and an already-revenue-generating business; other business models show different fields.

Northstar Notes is a fictional B2B subscription business. Every number below is a teaching assumption, not a benchmark or a recommendation. Use a separate practice model; replace these values before making business decisions.

Operating currency

USD

Current monthly subscription revenue

10,000

Current paid company customers

100

Monthly new paid company customers

10

Monthly paid-company retention

98%

Monthly non-headcount OpEx, excluding marketing

2,000

Monthly non-headcount marketing

500

Team / monthly base salary per person

2 people / 3,000

Current cash

100,000

Check the units: 10,000 ÷ 100 = USD 100 per customer per month. Non-headcount spend is (2,000 + 500) × 12 = USD 30,000 per year, excluding payroll. Base salaries total USD 6,000 per month before employer costs. Retention of 98% means 2% churn for the same monthly cohort; do not enter 2 in a retention field. These checks do not predict the final forecast, which also depends on timing, costs and other assumptions.

1. 01

   Choose an agent with browser control

   A text-only chat cannot fill the browser for you. Use an agent that supports browser interaction and can access the Tessly tab you choose. Browser support, permissions and availability depend on that provider; this is not a built-in Tessly agent.

2. 02

   Sign in and open the practice model yourself

   Use Open Tessly, complete sign-in yourself and open the intended practice model. Never paste passwords, verification codes or session tokens into a prompt. Confirm the model and operating currency before handing over control.

3. 03

   Provide what you have and set the limits

   Give the agent the Northstar Notes example or your current notes, spreadsheet excerpts and assumptions. The material can be incomplete. Ask the agent to identify visible fields, separate confirmed values from questions and propose a mapping before it types anything. Review that mapping first; do not let it replace unrelated assumptions.

4. 04

   Let the agent enter values in small groups

   Work through Revenue, Cost, Growth and Cash & Funding. The agent should read field labels, enter plain values and re-check what the interface shows. If a label, value or required choice is unclear, it should stop and ask. You can complete unsupported controls manually.

5. 05

   Review before final actions

   Inspect the entered values and any remaining defaults. Changes may already be retained by the app, so do not rely on a final save button as an undo boundary. Require your confirmation before Generate Forecast, save, overwrite, delete or share actions. Afterwards, compare the model with the input checklist.

See the field-by-field manual tutorial →

Select the prompt text and copy it. Replace the bracketed placeholders before using it.

• The intended model and operating currency match your checklist.
• Subscription baseline shows 100 customers and USD 10,000 monthly revenue; derived average is USD 100.
• New customers and retention are monthly inputs; retention is 98, not 0.98 or 2, in the percent field.
• Non-headcount costs and marketing are separate; salaries are not counted twice.
• Starting cash is USD 100,000; future funding, delivery costs, employer costs and dates have been reviewed.
• The model has no unexplained missing inputs. Review results and remaining defaults before saving or sharing.