Stress-test decisions and compare plans API

Get an honest second opinion on a plan or decision before you act. A devil's advocate proposes a different Plan B and names what your plan overlooks and its

Input

Send these Fields as input. A Field not listed here is refused.

plan

Plan to review

  • Type: string
  • Required: yes
  • Length in characters: 1 to 30000

goal

Goal and constraints

  • Type: string
  • Required: no
  • Length in characters: at most 30000

context

Background (optional)

  • Type: string
  • Required: no
  • Length in characters: at most 30000

Run it

One call presses the Widget and answers the run once its status is succeeded or failed, however long it takes. The key is read from ABYSS_API_KEY. Install the library with npm install abysshub or pip install abysshub; cURL sends the Fields as a form.

JavaScript

// index.mjs
import Abyss from "abysshub";

const abyss = new Abyss();

const run = await abyss.run("widget_387", {
  plan: "Open a second bakery shop across town in March. We take a 5-year lease on a 60 m2 corner unit near the central station, fit it out for about 85,000 EUR (oven, counter, seating for 12), and hire 3 new staff. Bread and pastries are baked at our first shop at 4 a.m. and driven over by van at 6 a.m. We finance it with a bank loan of 70,000 EUR and 15,000 EUR of savings.",
  goal: "Grow yearly revenue by at least 40% within 2 years without the owners working more than today. The second shop must break even within 12 months. Total budget 85,000 EUR; we cannot raise more.",
  context: "Our first shop has run for 6 years in a residential area and makes about 420,000 EUR a year with 7 staff. Its kitchen runs at about 70% capacity. The station area has two chain bakeries and heavy commuter traffic from 6 to 9 a.m., and little on weekends. The owners work about 55 hours a week each.",
});

console.log(run.result);
for (const path of await run.save("output")) {
  console.log(path);
}

Python

from abysshub import Abyss

abyss = Abyss()

run = abyss.run("widget_387", {
    "plan": "Open a second bakery shop across town in March. We take a 5-year lease on a 60 m2 corner unit near the central station, fit it out for about 85,000 EUR (oven, counter, seating for 12), and hire 3 new staff. Bread and pastries are baked at our first shop at 4 a.m. and driven over by van at 6 a.m. We finance it with a bank loan of 70,000 EUR and 15,000 EUR of savings.",
    "goal": "Grow yearly revenue by at least 40% within 2 years without the owners working more than today. The second shop must break even within 12 months. Total budget 85,000 EUR; we cannot raise more.",
    "context": "Our first shop has run for 6 years in a residential area and makes about 420,000 EUR a year with 7 staff. Its kitchen runs at about 70% capacity. The station area has two chain bakeries and heavy commuter traffic from 6 to 9 a.m., and little on weekends. The owners work about 55 hours a week each.",
})

print(run.result)
for path in run.save("output"):
    print(path)

cURL

curl https://api.abysshub.com/v1/widgets/widget_387/runs \
  -H "Authorization: Bearer $ABYSS_API_KEY" \
  -F 'plan=Open a second bakery shop across town in March. We take a 5-year lease on a 60 m2 corner unit near the central station, fit it out for about 85,000 EUR (oven, counter, seating for 12), and hire 3 new staff. Bread and pastries are baked at our first shop at 4 a.m. and driven over by van at 6 a.m. We finance it with a bank loan of 70,000 EUR and 15,000 EUR of savings.' \
  --form-string 'goal=Grow yearly revenue by at least 40% within 2 years without the owners working more than today. The second shop must break even within 12 months. Total budget 85,000 EUR; we cannot raise more.' \
  -F 'context=Our first shop has run for 6 years in a residential area and makes about 420,000 EUR a year with 7 staff. Its kitchen runs at about 70% capacity. The station area has two chain bakeries and heavy commuter traffic from 6 to 9 a.m., and little on weekends. The owners work about 55 hours a week each.'

A succeeded run carries its result and its output_files. Their URLs are signed for each read: re-read the run, never store a URL. A run still queued or running in the answer (after an hour, or when the API is busy) is read again at its Location with ?wait=true.

What it answers

The Example Run's result, the JSON the Widget wrote to output/output.json:

{
  "complete": true,
  "recommendation": "mixed",
  "review": {
    "summary": "Plan A adds a second fixed-cost shop: a 5-year lease, 85k EUR fit-out, three hires and a daily 4 a.m. bake with a 6 a.m. van run. It is an irreversible bet on untested station demand, and it does not show the arithmetic for 12-month break-even or for keeping owner hours flat. Plan B grows revenue from the existing kitchen's roughly 30% spare capacity through wholesale and commuter pre-orders, with a much smaller fixed-cost base and staged commitments. Plan B is stronger on risk and cost, but its 170k EUR target equals the full 40% growth goal with no slack, and its account acquisition is assumed rather than evidenced. The better course is a mixed approach: lead with Plan B now, and treat a station shop as a later option that is gated on proven demand.",
    "plan_a_strengths": [
      "Adds physical retail presence at a high-footfall location (central station, commuter peak 6-9 a.m.), which could build brand awareness beyond the residential area.",
      "Creates capacity for growth beyond the existing kitchen's limits, since a second shop is not constrained by the first shop's roughly 70% utilization.",
      "Diversifies revenue across two locations, so one site's problems do not fully hit the business.",
      "Has a concrete, costed budget for fit-out, lease and financing, which gives the owners a clear picture of the capital commitment.",
      "Uses a proven concept and product line from a shop that has traded successfully for six years."
    ],
    "plan_a_weaknesses": [
      "Omits the production and logistics model's real costs: the 4 a.m. bake, the 6 a.m. van run, loading and unloading, and a second early shift are not costed or staffed. Product also arrives about 2.5 hours old at the start of the peak.",
      "Three hires cannot cover opening hours of roughly 6 a.m. to 7 p.m. across seven days with two people per shift, so owners will likely fill the gaps, which breaks the goal of flat owner hours.",
      "No P&L, rent figure, wage estimate, working-capital estimate or break-even revenue. Illustrative figures suggest fixed costs of roughly 16-20k EUR a month, implying about 25-30k EUR monthly sales to break even, well above the 168k EUR a year needed for the growth goal and hard to reach in 12 months.",
      "Only 15k EUR of savings against personal liability on a 5-year lease and a 70k EUR loan. A 10-20% fit-out overrun would consume most of the savings, and there is no contingency.",
      "Demand at the station site is assumed. The two chain bakeries are entrenched, the first shop's customers are residential rather than commuter, and weekend trade is weak, so about 2 of 7 trading days carry little demand.",
      "Commits about 85k EUR of largely irreversible spending before any demand is tested or any losses are capped, which makes the downside large and hard to reverse.",
      "Loan terms, lease terms (rent-free period, break clause, deposit) and fit-out contractor quotes are unknown, so the financing case cannot be checked."
    ],
…

More

Keys, files, errors and limits: API access.