Baue KI-Agenten, die die Arbeit erledigen.

Ein Agent sammelt planmäßig Preise, Anzeigen und Jobs von mehreren Diensten, räumt alles in eine Tabelle und meldet sich nur bei echten Änderungen.

Du beschreibst eine Quelle einmal: URL, Pagination und benötigte Felder. Der Agent lädt die Seite, das Modell extrahiert Felder in ein festes Schema, Einträge werden über einen stabilen Key dedupliziert, ein Snapshot wird gespeichert und ein Diff zum letzten Lauf geschrieben.

Build a scraping and monitoring agent.

Data: table "sources" (name, url, pagination_pattern, selector_hint, fields jsonb, interval_minutes, active). Table "runs" (source_id, status, items_found, error, started_at, finished_at). Table "items" (source_id, raw_key unique per source, title, price numeric, currency, url, published_at, payload jsonb, first_seen_at, last_seen_at). Table "item_changes" (item_id, field, old_value, new_value, created_at).

Server: an edge function that takes a source id, fetches the page with a normal user agent, strips scripts, styles and navigation, trims the text to the listing area, then asks the model to extract rows into a strict JSON schema with temperature zero and null for missing values. Upsert rows into items on raw_key and insert item_changes whenever a tracked field differs. Log every attempt into runs, retry twice with backoff on network errors and respect a per source rate limit. Follow pagination up to a configurable page limit.

Automation: a scheduled job that picks active sources whose interval has elapsed, runs them one by one, then sends a digest email or webhook containing only item_changes created since the previous digest.

UI: sources page with add and edit form, health badge from the last run, run history with error text, items table with search and filters, a change feed and a CSV export button.

Rules: only public pages, honour robots.txt, keep all keys and model calls on the server, enable row level security so each user sees only their own sources and items.

Der erste Agent, den fast jedes Team braucht: Er liest dein Hilfecenter und antwortet Kunden nachts um drei, ohne Richtlinien zu erfinden.

Docs hochladen, in Chunks teilen, Embeddings speichern und nur mit gefundenen Passagen plus Quelle antworten. Ohne Treffer eskaliert der Agent an einen Menschen, statt zu raten.

Build a documentation support agent.

Data: a table "documents" (title, url, content) and a table "chunks" (document_id, content, embedding vector). A table "escalations" (question, email, created_at, status).

Server: one edge function that embeds the user question, retrieves the six closest chunks, and streams an answer that uses only those chunks. Every answer must end with the source links it used. If similarity is below the threshold, return a short "I do not have this in the docs" answer and insert a row into escalations.

UI: a chat page with streaming responses, message history in the browser, source links rendered as chips under each answer, and an escalation form that appears when the agent cannot answer.

Enable row level security on all tables, keep model calls on the server, and show a clear error state when the request fails.

Ersetze das Kontaktformular, das niemand ausfüllt, durch einen Agenten, der vier Fragen stellt und den Termin selbst bucht.

Der Agent führt ein kurzes strukturiertes Interview, bewertet den Lead nach deinen Kriterien, schreibt das Ergebnis in die Datenbank und schickt eine Zusammenfassung an den Vertrieb.

Build a lead qualification agent widget.

Behaviour: the agent asks at most five questions, one at a time, to learn company size, budget range, timeline and the problem being solved. It never asks two questions in one message and never asks for data it already has.

After the interview, produce a structured result with fields: score, tier, summary, next_step. Keep the schema flat and unconstrained, state the ranges in the prompt text, and clamp values in code.

Storage: insert into a "leads" table with contact details, transcript, score, tier and created_at. Send a notification email with the summary.

UI: a floating chat bubble on the landing page, mobile friendly, with a typing indicator and a final card showing the booked next step.

Ein mehrstufiger Agent, der sucht, liest, vergleicht und ein belegtes Briefing liefert statt eines selbstsicheren Absatzes.

Definiere drei Tools: Suche, Seite laden, Fund speichern. Lass den Agenten loopen, bis genug Belege da sind, und zeige die Tool-Timeline in der UI.

Build a research agent with tool calling.

Tools: web_search(query), fetch_page(url), save_finding(claim, source_url, confidence). Give each tool a narrow input schema and a short description.

Loop: allow at least fifty steps, stop when the agent has five saved findings or decides the question is answered. Never let the agent answer without at least two independent sources.

Output: a brief with a one paragraph answer, a bullet list of findings, and a sources section. Save the brief to a "reports" table.

UI: stream the answer, render every tool call as a timeline row with its input and a compact result, and add a copy button plus markdown export.

Einen Artikel einfügen und Newsletter, Thread, Carousel-Skript und Video-Hook im eigenen Ton erhalten.

Ein Voice-Profil mit Regeln und verbotenen Phrasen speichern und jedes Format in einem eigenen Call erzeugen, damit die Texte scharf bleiben.

Build a content repurposing agent.

Input: a long article plus a saved voice profile (tone rules, favourite words, banned phrases, audience).

Generate four outputs in separate calls so each one is focused: a newsletter intro, a social thread of six posts, a carousel script of seven slides, and three video hooks.

Rules for every output: no em dashes, no emoji, no filler phrases like "in today's fast paced world", short sentences, concrete nouns.

UI: one input panel on the left, four result cards on the right, each editable inline with a copy button and a regenerate button that only regenerates that card.

Jeder Gründer ertrinkt in denselben vierzig Mails. Dieser Agent sortiert sie, entwirft Antworten und fragt vor dem Senden.

Nachrichten in wenige Intents klassifizieren, eine Aktion vorschlagen und für alles Ausgehende eine Freigabe verlangen.

Build an inbox triage agent.

For each incoming message, classify it as one of: sales, support, partnership, invoice, noise. Add urgency low, medium or high, and a one sentence reason.

Draft a reply for every message that is not noise, using saved templates as the base and matching the sender's language.

Any action that sends an email or changes external state must require approval in the UI first. Show the draft, the intent and the reason on an approval card with approve, edit and discard.

UI: a triage queue grouped by intent, keyboard shortcuts for approve and skip, and a daily digest view of what was handled.

Praxen, Salons und Werkstätten verpassen weiterhin die Hälfte der Anrufe. Ein Voice-Agent nimmt sofort ab und trägt den Termin direkt ein.

Spracherkennung rein, kurzer skriptierter Dialog, Sprachausgabe raus und eine Bestätigung, die der Anrufer prüfen kann.

Build a voice booking agent.

Flow: transcribe the caller audio, run a slot filling dialogue that collects service, preferred day, preferred time and phone number, confirm the details out loud, then create the booking.

Never invent availability. Check the bookings table first and offer the two closest free slots when the requested time is taken.

Confirm by reading the booking back and sending a text summary. Store the full transcript with the booking for review.

UI: an operator dashboard with today's calls, transcripts, created bookings and a flagged list of calls the agent could not finish.

Die meiste Abwanderung passiert in den ersten zehn Minuten. Ein Agent, der weiß, wo der Nutzer hängt, verbessert die Aktivierung mehr als jede Tooltip-Tour.

Dem Agenten die erledigten Schritte und den aktuellen Screen geben, damit er genau die nächste Aktion vorschlägt und per Tool ausführt.

Build an in-app onboarding copilot.

Context: pass the current route, the list of completed setup steps and the last three user events into the system prompt on every call.

Behaviour: always propose exactly one next action, explain in one sentence why it matters, and offer to do it. Never list five options.

Tools: create_project, invite_teammate, connect_data_source. Mark every tool as needing approval, and show the approval card inline in the chat.

UI: a slide-over panel available from every page, a progress checklist at the top, and an admin view showing where users get stuck most often.

Frage in normaler Sprache stellen, Chart plus die zugrunde liegende Query erhalten. Die offene Query schafft Vertrauen.

Dem Agenten das Schema geben, auf Read-only-Views beschränken, die Query serverseitig ausführen und das Ergebnis als Chart mit sichtbarem SQL rendern.

Build a data analyst agent over a read-only schema.

Safety: expose only read-only views, reject anything that is not a select, cap rows returned, and run every query server side with a timeout.

Behaviour: the agent writes the query, explains in one sentence what it measures, then picks the chart type that fits the shape of the result.

UI: a question box with example questions, a chart, a collapsible SQL block, and a saved questions list that can be rerun with one click.

Handle empty results and query errors explicitly with a plain language message and a suggested fix.

Kein weiterer Artikel-Spinner. Der Agent liest die aktuelle Suchergebnisseite, findet die Lücke und briefed eine Seite, die den Klick verdient.

Top-Ergebnisse sammeln, Überschriften extrahieren, Subthemen clustern und ein Outline mit den fehlenden Blickwinkeln plus internen Linkzielen ausgeben.

Build an SEO brief agent.

Input: a target keyword and the site the page will live on.

Steps: search the keyword, fetch the top eight results, extract their headings and word counts, cluster the shared subtopics, and list the questions none of them answer well.

Output a brief with: search intent in one line, target title and description, an H2 outline, entities to mention, three internal link targets from the given site, and the differentiating angle.

UI: a single input, a progress list of the steps as they run, and the finished brief in a copyable panel with markdown export.

Filter vertreiben Kunden. Ein kurzes Gespräch über den echten Bedarf bringt sie kaufbereit zur Produktseite.

Der Agent fragt nach Anwendungsfall und Einschränkungen, fragt den Live-Katalog ab und liefert drei Optionen mit klarem Vergleich.

Build a shopping assistant agent for an online store.

Tools: search_products(query, filters), get_product(id), check_stock(id).

Behaviour: ask at most three questions about use case, budget and any dealbreaker, then recommend exactly three products. For each one, give the reason it fits and the honest downside. Never recommend an out of stock item.

UI: chat with product cards inline, each card showing image, price, stock status and an add to cart button. Keep the conversation on the product page as a side panel.

Log every conversation with the products shown and whether the visitor added to cart, so the store can measure assisted revenue.

Zweihundert Bewerbungen, eine ehrliche Scorecard pro Kandidat und ein Protokoll, warum so entschieden wurde.

Lebenslauf parsen, gegen die eigenen Kriterien bewerten, zwei Rückfragen per Mail stellen und die Shortlist mit Begründung an einen Menschen geben.

Build a recruiting screening agent.

Input: a job description with must have and nice to have criteria, plus uploaded resumes.

For each candidate produce: a score per criterion, an overall recommendation, the strongest evidence quoted from the resume, and the biggest open question.

Never infer age, gender, nationality or anything the criteria do not mention, and never reject a candidate automatically. The agent proposes, a human decides.

UI: a candidate table sorted by score with expandable scorecards, a compare view for the top five, and a one click email that asks the open question.

Kontoauszug hochladen, Kategorien, Trends und einen unangenehmen Satz über das vergessene Abo bekommen.

Datei parsen, Transaktionen kategorisieren, wiederkehrende Abbuchungen erkennen und Rückfragen zu den eigenen Zahlen erlauben.

Build a personal spending agent.

Input: a CSV bank statement uploaded by the user.

Processing: normalise dates and amounts, categorise every transaction using rules first and the model only for the leftovers, and detect recurring charges by matching merchant and cadence.

Output: a summary with total by category, month over month change, the three largest changes explained in one sentence each, and a list of subscriptions with their yearly cost.

UI: upload area, a category chart, a transactions table with inline category editing that retrains the rules, and a chat box for follow up questions about the uploaded data only.

Keep all data private to the signed in user with row level security.

Ein Chatfenster, das CRM, Docs und Billing liest und die langweilige Aufgabe erledigt, für die sonst fünf Tabs offen sind.

Das Model Context Protocol hat Tool-Zugriff standardisiert. Statt einer eigenen Integration pro Dienst bekommt der Agent eine Liste typisierter Tools und wählt zur Laufzeit das passende. Du pflegst ein Verbindungsregister, eine Rechtekarte je Rolle und ein Log aller Aufrufe.

Build an internal tool-calling agent with a typed tool registry.

Data: connections (user_id, service, label, status), tools (name, description, args_schema, mode read or write), tool_calls (tool, args, result, duration_ms, cost), approvals (tool_call_id, status).

Server: one function that returns the tools allowed for the current user role, one function that executes a tool after validating arguments against args_schema, and one that records the call.

Agent loop: the model receives the allowed tool list, chooses at most one tool per turn, and must explain in one sentence why it chose it.

Safety: any tool marked write requires an approval card showing the exact arguments before it runs. Never execute a write tool without a recorded approval row.

UI: chat panel, a connections page with a test-run button, and a run timeline showing each tool call with duration and cost.

Protect every table with row level security so a user only ever sees their own connections and calls.

Der meistgesuchte Agent des Jahres. Er nimmt eine Firmenliste, findet den Anlass, schreibt eine Nachricht ohne Template-Geruch und legt die Antwort in deinen Kalender.

Der Wert liegt nicht in mehr Mails, sondern im Rechercheschritt. Der Agent sammelt je Firma öffentliche Signale, bewertet den Fit zum Wunschkundenprofil, verwirft alles unter der Schwelle und entwirft erst dann. Jeder Entwurf wartet auf einen menschlichen Klick.

Build an AI SDR agent focused on research quality, not send volume.

Data: accounts (name, domain, size, notes), signals (account_id, type, text, source_url, found_at), fit_scores (account_id, score, reason), drafts (account_id, subject, body, status), replies (draft_id, category, next_step).

Pipeline: import accounts from CSV, research each account and store at least one signal with a source URL, score fit from 0 to 100 against a stored ideal customer profile, and draft only for accounts above the threshold.

Writing rule: every draft must quote exactly one stored signal and stay under 90 words. If no signal exists, skip the account and say why.

Human control: drafts land in an approval queue with inline editing. Nothing sends without an approved row and a per-day send cap.

Replies: classify each reply as interested, not now, or not a fit, and surface interested ones with a suggested meeting time.

UI: pipeline board, an account page showing signals with source links, and a draft queue with approve, edit and skip.

Zwölf fragile Szenarien, drei Tools, niemand weiß, welches die Rechnung schickt. Bündle alles in eine App, in der jeder Lauf sichtbar ist und jeder Fehler einen Namen hat.

Deterministische Schritte bleiben deterministisch. Das Modell kommt nur dort zum Einsatz, wo Urteilsvermögen nötig ist. Der Rest ist normaler Code nach Zeitplan, was das Ganze günstig und angenehm langweilig macht.

Build a workflow runner app where an AI step is used only for judgement.

Data: workflows (name, schedule, active), steps (workflow_id, position, kind rule or model, config), runs (workflow_id, started_at, status), run_steps (run_id, step_id, input, output, duration_ms, error), dead_letters (run_id, payload, reason).

Execution: run steps in order, store input and output of every step, retry a failed step three times with growing delay, then write it to dead_letters and stop the run.

Model steps: must return exactly one value from a fixed list defined in the step config, with a one sentence reason stored alongside.

UI: workflow list with last run status, a run timeline showing each step with duration and output, a manual run button, and a dead letter screen with a retry action.

Keep secrets in server functions only and protect every table with row level security.

Eine Praxis, ein Salon oder eine Werkstatt verpasst ein Drittel der Anrufe. Jeder davon ist ein zahlender Kunde, der die nächste Nummer wählt.

Der Agent nimmt ab, beantwortet die fünf Standardfragen, prüft den Kalender, bucht oder nimmt eine Nachricht auf und schickt dem Inhaber eine Zusammenfassung. Entscheidend ist der Fallback: klingt der Anrufer genervt oder fragt außerhalb des Skripts, bietet der Agent einen Menschen an.

Build an AI receptionist for a local business.

Data: business_profile (hours, services, prices, address, five FAQ pairs), calls (started_at, caller, outcome), transcripts (call_id, role, text, confidence), bookings (service, slot, caller, status hold or confirmed), messages (call_id, text, callback_number).

Behaviour: greet, identify the request, answer only from business_profile, check available slots, place a hold, confirm, then release or confirm the hold.

Limits: answers stay under two sentences. If the model cannot answer from business_profile, or the caller sounds frustrated, offer a callback and store the number instead of guessing.

After the call: generate a summary with outcome, next step and a link to the transcript, and send it to the owner.

UI: a text chat to test the same logic without voice, a call log with transcripts, a bookings calendar, and an editable business profile page.

Der am schnellsten gebaute Agent und der beste für Demos. Ein Gedanke rein, sieben Hooks, sieben Skripte und Captions raus.

Die Stimme ist das Produkt. Der Agent speichert zehn Beispiele deines echten Schreibstils, extrahiert einmal die Muster und wendet sie auf jedes Skript an.

Build a short video script agent that writes in the user's own voice.

Setup: the user pastes ten samples of their own writing. Extract a voice profile once with tone, sentence length, favourite structures and banned words, and store it.

Input: one idea in a sentence.

Output: seven hooks scored for curiosity and clarity, the best three expanded into 40 second scripts using hook, tension, payoff and call to action, plus a caption and five tags for each.

Rules: no generic openers, no words from the banned list, and every script must be readable out loud in under 45 seconds.

UI: idea input, a scored hook list, a script editor, and a weekly calendar where scripts can be dragged between days.

Ein Brief rein, ein fertiger Spot raus: Skript, Storyboard, Voice-over, Untertitel und drei Schnitte für verschiedene Platzierungen.

Der Agent arbeitet in Stufen statt in einem Riesenprompt: Angebot und Versprechen, dann Shotlist mit Dauer je Einstellung, dann getimtes Voice-over, dann Schnitt und eingebrannte Untertitel. Jede Stufe wird gespeichert, eine Szene lässt sich einzeln neu schreiben.

Build an ad video agent that turns a product brief into a finished commercial.

Data: briefs (product, buyer, pain, promise, proof), scripts (brief_id, angle, status), shots (script_id, index, seconds, visual, voice_over, on_screen_text, clip_url), renders (script_id, aspect, url, status).

Flow, one stage at a time and each stage saved before the next:
1. From the brief, propose three angles with a one line promise each. Wait for the user to pick one.
2. Build a shot list as rows with index, seconds, visual, on screen text. Total duration must equal the chosen placement length of 15, 30 or 60 seconds.
3. Write the voice over per shot, sized to that shot's seconds at about 2.5 words per second.
4. Attach a clip to each shot, then queue renders for 9:16, 1:1 and 16:9 with burned in word level subtitles.

Rules: one promise per ad, the hook lands in the first two seconds, no claim that is not backed by the proof field, and never exceed the placement length.

UI: brief form, angle picker, an editable shot table where changing seconds re-times only that shot's voice over, a render queue with status, and a version list to compare cuts side by side.

Paid Social scheitert nicht am Schnitt, sondern an den ersten zwei Sekunden. Der Agent liefert zwanzig Hooks pro Produkt und macht die besten zu drehfertigen Creator-Briefings.

Das Ergebnis ist kein Skript, sondern ein Drehkit: Hook, Handlung pro Beat, gesprochene Zeile, Caption und Thumbnail-Frame. Jede Variante hat einen Tracking-Namen, sodass Ergebnisse zurückfließen.

Build a UGC ad script agent that produces shot ready creator briefs and learns from results.

Data: products (name, promise, proof, audience), hooks (product_id, family, line, curiosity_score, clarity_score, claim_risk), variants (hook_id, beats json, caption, tags, tracking_name), results (tracking_name, spend, views, clicks, conversions).

Hook families: problem, contrast, mistake, result, demo, story. Generate three hooks per family, score each from one to five on curiosity and clarity, flag any claim not supported by the proof field, keep the top eight and discard the rest.

For each surviving hook produce four beats of five seconds: hook, problem, demo, call to action. Every beat states what is in frame, what the creator does with their hands, and the exact line spoken. Add a caption, three tags and a tracking name of the form product-family-number.

Results loop: accept a CSV of results by tracking name, compute cost per click per hook family, and weight the next generation toward the winning families.

UI: product form, a scored hook table, a beat editor, a print view of the creator brief, and a results dashboard by hook family.

Nimm einen unordentlichen Fünf-Minuten-Walkthrough auf und erhalte eine 60-Sekunden-Demo mit Narration, Zoom auf jeden wichtigen Klick und sauberen Untertiteln.

Die Transkription ist nur der Einstieg. Der Agent verknüpft Text mit Momenten, entfernt Stille und Wiederholungen, schreibt die Narration nutzenorientiert um und setzt Zoom-Marker auf Klick-Timestamps.

Build a product demo video agent that turns a raw screen recording into a short polished demo.

Data: recordings (file_url, duration, target_length), words (recording_id, text, start, end), segments (recording_id, start, end, task, narration, importance), markers (segment_id, timestamp, type zoom or highlight, region), exports (recording_id, aspect, url, status).

Pipeline: transcribe with word level timestamps, remove silences longer than 0.6 seconds and repeated sentence starts, group the rest into segments where one segment equals one task the product performs, rewrite each segment into a single benefit sentence, score segments by importance and keep only enough to fit the target length.

Then place a zoom marker at every click timestamp and a highlight on the region that changed, render with word level subtitles and export 16:9 and 9:16 from the same edit.

Rules: narration describes the outcome, not the interface. Never say click here. Total length must not exceed the target. Keep every cut reversible by storing segments rather than rewriting the source file.

UI: upload page, a segment timeline where segments can be reordered, muted or restored, a narration editor with live duration, a marker overlay on the preview, and an export panel per aspect ratio.