Skip to content
Adaptive Systems
Menu
Open Front DeskOpen DocketOpen DossierOpen Pestle

Live system

All four products, as they run.

Everything below is fetched by your browser from the public endpoints. The activity feeds show our own test and demo runs labelled as such; Front Desk's counters count real traffic only. No personal data, message text, call transcript or document content is ever exposed.

Front Desk

Live
Leads scored
real leads; tests excluded
Knowledge chunks
1536-dim vectors in pgvector
Policy gate
average deterministic decision
Services up
health-checked every minute

Leads scored per day · 14 days

Live
…max … a day
0000-00-0: Full offer 0, Starter 0, Needs info 0, Human review 0, Reject 000-00000-00-1: Full offer 0, Starter 0, Needs info 0, Human review 0, Reject 00000-00-2: Full offer 0, Starter 0, Needs info 0, Human review 0, Reject 00000-00-3: Full offer 0, Starter 0, Needs info 0, Human review 0, Reject 000-30000-00-4: Full offer 0, Starter 0, Needs info 0, Human review 0, Reject 00000-00-5: Full offer 0, Starter 0, Needs info 0, Human review 0, Reject 00000-00-6: Full offer 0, Starter 0, Needs info 0, Human review 0, Reject 000-60000-00-7: Full offer 0, Starter 0, Needs info 0, Human review 0, Reject 00000-00-8: Full offer 0, Starter 0, Needs info 0, Human review 0, Reject 00000-00-9: Full offer 0, Starter 0, Needs info 0, Human review 0, Reject 000-90000-00-10: Full offer 0, Starter 0, Needs info 0, Human review 0, Reject 00000-00-11: Full offer 0, Starter 0, Needs info 0, Human review 0, Reject 00000-00-12: Full offer 0, Starter 0, Needs info 0, Human review 0, Reject 000-120000-00-13: Full offer 0, Starter 0, Needs info 0, Human review 0, Reject 000-13
  • Full offer
  • Starter
  • Needs info
  • Human review
  • Reject

Lead routes · all time

—
  • Full offer—
  • Starter—
  • Needs info—
  • Human review—
  • Reject—

Live activity · last 7 days

Service response time · now

Uptime · last 48 checks · 24 h

Loading monitors… or see the status page.

Models and index

Primary LLM
Fallback chain
Embeddings
Risk engine
Vector index

Docket

Live
Documents processed
… in the last 24 h
Values verified
found on the page + passed the checks
Straight through
no person needed (demo set: half are built to be caught)
Median time
upload to decision, all checks included

At a glance

—
Values verified

found on the page and passed every check

—
Straight through

no person needed (half the demo set is built to be caught)

—
Scans read twice

scanned pages also read by OCR

—
Second opinion agrees

TypeSafe Jev vs the risk gate

Documents per day · 14 days

Live
…max … a day
0000-00-0: Straight through 0, Waited for a person 0, Rejected 000-00000-00-1: Straight through 0, Waited for a person 0, Rejected 00000-00-2: Straight through 0, Waited for a person 0, Rejected 00000-00-3: Straight through 0, Waited for a person 0, Rejected 000-30000-00-4: Straight through 0, Waited for a person 0, Rejected 00000-00-5: Straight through 0, Waited for a person 0, Rejected 00000-00-6: Straight through 0, Waited for a person 0, Rejected 000-60000-00-7: Straight through 0, Waited for a person 0, Rejected 00000-00-8: Straight through 0, Waited for a person 0, Rejected 00000-00-9: Straight through 0, Waited for a person 0, Rejected 000-90000-00-10: Straight through 0, Waited for a person 0, Rejected 00000-00-11: Straight through 0, Waited for a person 0, Rejected 00000-00-12: Straight through 0, Waited for a person 0, Rejected 000-120000-00-13: Straight through 0, Waited for a person 0, Rejected 000-13
  • Straight through
  • Waited for a person
  • Rejected

How documents were routed

—
  • Straight through—
  • Waited for a person—
  • Rejected—

Document types

Currencies read

—currencies

    Median reading time per model

    Accuracy · the model in production

    Caught by the risk gate

    Live activity

    Dossier

    Live
    Applicants checked
    cases, all documents compared
    Documents processed
    statements, bills, payslips, IDs
    Failed checks
    cases with a forged or mismatched document
    Per document
    median: read, examined and checked

    Applicants per day · 14 days

    Live
    …max … a day
    0000-00-0: Consistent 0, Needs a person 0, Failed checks 000-00000-00-1: Consistent 0, Needs a person 0, Failed checks 00000-00-2: Consistent 0, Needs a person 0, Failed checks 00000-00-3: Consistent 0, Needs a person 0, Failed checks 000-30000-00-4: Consistent 0, Needs a person 0, Failed checks 00000-00-5: Consistent 0, Needs a person 0, Failed checks 00000-00-6: Consistent 0, Needs a person 0, Failed checks 000-60000-00-7: Consistent 0, Needs a person 0, Failed checks 00000-00-8: Consistent 0, Needs a person 0, Failed checks 00000-00-9: Consistent 0, Needs a person 0, Failed checks 000-90000-00-10: Consistent 0, Needs a person 0, Failed checks 00000-00-11: Consistent 0, Needs a person 0, Failed checks 00000-00-12: Consistent 0, Needs a person 0, Failed checks 000-120000-00-13: Consistent 0, Needs a person 0, Failed checks 000-13
    • Consistent
    • Needs a person
    • Failed checks

    Outcomes · all time

    —
    • Consistent—
    • Needs a person—
    • Failed checks—

    Detection · published eval

    Caught so far

    Live activity

    Pestle · AI phone calls on Retell + Twilio

    Live

    The pharmacy voice agent's own numbers, from its API: every call to the two fictional demo pharmacies, on the phone line or in the browser. Outcomes and reasons are fixed labels; no caller number, name or transcript leaves the staff app. Call it yourself.

    Calls handled
    phone + browser
    Resolved by AI
    no person needed
    AI minutes
    speech in and out
    Cost a minute
    Retell + Twilio, as they report it

    Calls per day · 14 days

    Live
    …max … a day
    0000-00-0: Resolved by AI 0, Handed to a person 0, Other 000-00000-00-1: Resolved by AI 0, Handed to a person 0, Other 00000-00-2: Resolved by AI 0, Handed to a person 0, Other 00000-00-3: Resolved by AI 0, Handed to a person 0, Other 000-30000-00-4: Resolved by AI 0, Handed to a person 0, Other 00000-00-5: Resolved by AI 0, Handed to a person 0, Other 00000-00-6: Resolved by AI 0, Handed to a person 0, Other 000-60000-00-7: Resolved by AI 0, Handed to a person 0, Other 00000-00-8: Resolved by AI 0, Handed to a person 0, Other 00000-00-9: Resolved by AI 0, Handed to a person 0, Other 000-90000-00-10: Resolved by AI 0, Handed to a person 0, Other 00000-00-11: Resolved by AI 0, Handed to a person 0, Other 00000-00-12: Resolved by AI 0, Handed to a person 0, Other 000-120000-00-13: Resolved by AI 0, Handed to a person 0, Other 000-13
    • Resolved by AI
    • Handed to a person
    • Other

    Outcomes · all time

    —
    • Resolved by AI—
    • Put through to staff—
    • Callback requested—
    • Transfer not answered—

    Why people call · the AI's label

    Latest calls

    Sources

    See them run on real data.

    The apps run real models on every click, so they sit behind a password. Ask for a login or a guided walkthrough: talk to our AI receptionist in Front Desk, drop invoices into Docket, or load forged applicants into Dossier. Or try them in public: score a lead, read your invoice, forge an applicant, or connect Docket and Dossier to Claude. Or hire us to build yours.

    Ask for accessEverything on one page: the one-pager