> ## Documentation Index > Fetch the complete documentation index at: https://docs.mavera.io/llms.txt > Use this file to discover all available pages before exploring further. # Webinar Series Intelligence > Diagnose engagement shifts across a Vimeo webinar series — where audience interest peaks, drops, and recovers ### Scenario You run a webinar series on Vimeo — a multi-session program where engagement typically declines across sessions. This job pulls all videos from a Vimeo showcase (album/folder) representing the series, runs Video Analysis on each session, then asks Mave to diagnose engagement shifts: "How does engagement shift across this series? Where do we lose them?" The result is a session-by-session intelligence report that shows you exactly where audience interest peaks, drops, and recovers — so you can restructure future series for maximum retention. ### Architecture ```mermaid theme={"dark"} flowchart LR A["Vimeo GET /me/albums/{id}/videos"] --> B["Mavera POST /video-analysis"] --> C[Combine scores chronologically] --> D["POST /mave/chat (series arc)"] --> E[Session-by-session report] ``` ### Code ```python Python theme={"dark"} import os, requests, time VM = os.environ["VIMEO_ACCESS_TOKEN"] MV = os.environ["MAVERA_API_KEY"] VM_BASE = "https://api.vimeo.com" MV_BASE = "https://app.mavera.io/api/v1" VM_H = {"Authorization": f"Bearer {VM}", "Accept": "application/vnd.vimeo.*+json;version=3.4"} MV_H = {"Authorization": f"Bearer {MV}", "Content-Type": "application/json"} ALBUM_ID = "12345678" # 1. Fetch all videos in the showcase/album (series) album_resp = requests.get(f"{VM_BASE}/me/albums/{ALBUM_ID}/videos", headers=VM_H, params={ "per_page": 50, "sort": "manual", "fields": "uri,name,link,duration,stats,created_time,description", }).json() if "error" in album_resp: raise SystemExit(f"Vimeo API error: {album_resp.get('developer_message', '')}") sessions = [] for v in album_resp.get("data", []): vid_id = v["uri"].split("/")[-1] stats = v.get("stats", {}) sessions.append({ "id": vid_id, "name": v["name"], "link": v["link"], "duration": v.get("duration", 0), "plays": stats.get("plays", 0), "finishes": stats.get("finishes", 0), "finish_rate": round(stats.get("finishes", 0) / max(stats.get("plays", 1), 1) * 100, 1), "created": v.get("created_time", "")[:10], "description": v.get("description", "")[:200], }) # 2. Get album metadata album_meta = requests.get(f"{VM_BASE}/me/albums/{ALBUM_ID}", headers=VM_H, params={ "fields": "name,description,metadata.connections.videos.total", }).json() series_name = album_meta.get("name", f"Album {ALBUM_ID}") print(f"Series: \"{series_name}\" — {len(sessions)} sessions") # 3. Analyze each session via Mavera session_scores = [] for i, session in enumerate(sessions): print(f" Analyzing session {i+1}/{len(sessions)}: \"{session['name'][:40]}\"") upload = requests.post(f"{MV_BASE}/assets", headers=MV_H, json={ "url": session["link"], "name": f"[S{i+1}] {session['name'][:60]}", "type": "video", }).json() analysis = requests.post(f"{MV_BASE}/video-analysis", headers=MV_H, json={ "asset_id": upload["id"], "analysis_types": [ "emotional_arc", "hook_score", "pacing", "cognitive_load", "message_clarity", "behavioral_effectiveness", ], "metadata": {"session_number": i + 1, "series": series_name}, }).json() for _ in range(30): time.sleep(3) status = requests.get( f"{MV_BASE}/video-analysis/{analysis['id']}", headers=MV_H ).json() if status.get("status") == "completed": break r = status.get("results", {}) session_scores.append({ **session, "session_num": i + 1, "hook": r.get("hook_score", {}).get("score", 0), "emotion_avg": r.get("emotional_arc", {}).get("intensity_avg", 0), "emotion_peak": r.get("emotional_arc", {}).get("peak_intensity", 0), "clarity": r.get("message_clarity", {}).get("score", 0), "pacing_score": r.get("pacing", {}).get("score", 0), "cog_load": r.get("cognitive_load", {}).get("average", 0), "arc_summary": r.get("emotional_arc", {}).get("summary", ""), }) time.sleep(1) # 4. Series arc analysis via Mave session_block = "\n\n".join( f"SESSION {s['session_num']}: \"{s['name']}\"\n" f" Date: {s['created']} | Duration: {s['duration']}s | Plays: {s['plays']:,} | Finish Rate: {s['finish_rate']}%\n" f" Hook: {s['hook']}/100 | Emotion Avg: {s['emotion_avg']:.1f}/10 | Peak: {s['emotion_peak']:.1f}/10\n" f" Clarity: {s['clarity']}/100 | Pacing: {s['pacing_score']:.1f}/10 | Cog Load: {s['cog_load']:.1f}/10\n" f" Arc: {s['arc_summary'][:150]}" for s in session_scores ) series_analysis = requests.post(f"{MV_BASE}/mave/chat", headers=MV_H, json={ "message": f"""Analyze engagement patterns across this webinar series. SERIES: "{series_name}" ({len(session_scores)} sessions) {session_block} Produce: 1. **Engagement Arc**: How does audience engagement shift across sessions? Where does it peak and where does it drop? 2. **Drop-Off Diagnosis**: At which session do we lose the most viewers? What specifically about that session's creative quality explains the drop? 3. **Session Comparison**: Which session is the strongest and weakest? What makes them different? 4. **Pacing Pattern**: Does the series maintain energy or does it fatigue viewers? Is cognitive load increasing across sessions? 5. **Recommendations**: How should we restructure the next series to maintain engagement? Specific changes to session order, content density, and hook strategy. 6. **Recovery Opportunities**: Can we save the weakest session with a re-edit? What specifically should change?""", }).json() print(f"\nWEBINAR SERIES INTELLIGENCE — \"{series_name}\"") print("=" * 65) print(f"{'Session':<8} {'Title':<30} {'Plays':>7} {'Finish%':>8} {'Hook':>6} {'Emotion':>8} {'Clarity':>8}") print("-" * 65) for s in session_scores: print(f" S{s['session_num']:<5} {s['name'][:28]:<30} {s['plays']:>7,} {s['finish_rate']:>7.1f}% " f"{s['hook']:>5} {s['emotion_avg']:>7.1f} {s['clarity']:>7}") print("\n" + series_analysis.get("content", "")[:2500]) ``` ```javascript JavaScript theme={"dark"} const VM = process.env.VIMEO_ACCESS_TOKEN; const MV = process.env.MAVERA_API_KEY; const VM_BASE = "https://api.vimeo.com"; const MV_BASE = "https://app.mavera.io/api/v1"; const VM_H = { Authorization: `Bearer ${VM}`, Accept: "application/vnd.vimeo.*+json;version=3.4" }; const MV_H = { Authorization: `Bearer ${MV}`, "Content-Type": "application/json" }; const ALBUM_ID = "12345678"; // 1. Fetch series videos from album const albumResp = await fetch( `${VM_BASE}/me/albums/${ALBUM_ID}/videos?per_page=50&sort=manual` + `&fields=uri,name,link,duration,stats,created_time,description`, { headers: VM_H } ).then(r => r.json()); if (albumResp.error) throw new Error(albumResp.developer_message || albumResp.error); const sessions = (albumResp.data || []).map(v => { const stats = v.stats || {}; const plays = stats.plays || 0; const finishes = stats.finishes || 0; return { id: v.uri.split("/").pop(), name: v.name, link: v.link, duration: v.duration || 0, plays, finishes, finishRate: plays > 0 ? Math.round(finishes / plays * 1000) / 10 : 0, created: (v.created_time || "").slice(0, 10), description: (v.description || "").slice(0, 200), }; }); // 2. Album metadata const albumMeta = await fetch( `${VM_BASE}/me/albums/${ALBUM_ID}?fields=name,description`, { headers: VM_H } ).then(r => r.json()); const seriesName = albumMeta.name || `Album ${ALBUM_ID}`; console.log(`Series: "${seriesName}" — ${sessions.length} sessions`); // 3. Analyze each session const sessionScores = []; for (let i = 0; i < sessions.length; i++) { const session = sessions[i]; console.log(` Analyzing S${i + 1}: "${session.name.slice(0, 40)}"`); const upload = await fetch(`${MV_BASE}/assets`, { method: "POST", headers: MV_H, body: JSON.stringify({ url: session.link, name: `[S${i + 1}] ${session.name.slice(0, 60)}`, type: "video" }), }).then(r => r.json()); const analysis = await fetch(`${MV_BASE}/video-analysis`, { method: "POST", headers: MV_H, body: JSON.stringify({ asset_id: upload.id, analysis_types: ["emotional_arc", "hook_score", "pacing", "cognitive_load", "message_clarity", "behavioral_effectiveness"], metadata: { session_number: i + 1, series: seriesName }, }), }).then(r => r.json()); let status; for (let j = 0; j < 30; j++) { await new Promise(r => setTimeout(r, 3000)); status = await fetch(`${MV_BASE}/video-analysis/${analysis.id}`, { headers: MV_H }).then(r => r.json()); if (status.status === "completed") break; } const r = status.results || {}; sessionScores.push({ ...session, sessionNum: i + 1, hook: r.hook_score?.score || 0, emotionAvg: r.emotional_arc?.intensity_avg || 0, emotionPeak: r.emotional_arc?.peak_intensity || 0, clarity: r.message_clarity?.score || 0, pacingScore: r.pacing?.score || 0, cogLoad: r.cognitive_load?.average || 0, arcSummary: r.emotional_arc?.summary || "", }); await new Promise(r => setTimeout(r, 1000)); } // 4. Series analysis const sessionBlock = sessionScores.map(s => `SESSION ${s.sessionNum}: "${s.name}"\n Date: ${s.created} | ${s.duration}s | Plays: ${s.plays.toLocaleString()} | Finish: ${s.finishRate}%\n` + ` Hook: ${s.hook}/100 | Emotion: ${s.emotionAvg.toFixed(1)}/10 | Clarity: ${s.clarity}/100 | CogLoad: ${s.cogLoad.toFixed(1)}/10` ).join("\n\n"); const seriesAnalysis = await fetch(`${MV_BASE}/mave/chat`, { method: "POST", headers: MV_H, body: JSON.stringify({ message: `Analyze engagement across this webinar series.\n\nSERIES: "${seriesName}" (${sessionScores.length} sessions)\n\n${sessionBlock}\n\nProduce:\n1. Engagement arc across sessions\n2. Drop-off diagnosis — which session loses the most viewers and why\n3. Strongest vs weakest session comparison\n4. Pacing/fatigue pattern\n5. Restructuring recommendations for next series\n6. Recovery edits for weakest session`, }), }).then(r => r.json()); console.log(`\nWEBINAR SERIES INTELLIGENCE — "${seriesName}"`); console.log("=".repeat(65)); sessionScores.forEach(s => console.log(` S${String(s.sessionNum).padEnd(5)} ${s.name.slice(0, 28).padEnd(30)} ` + `${String(s.plays.toLocaleString()).padStart(7)} ${(s.finishRate + "%").padStart(8)} ` + `${String(s.hook).padStart(6)} ${s.emotionAvg.toFixed(1).padStart(8)} ${String(s.clarity).padStart(8)}`) ); console.log("\n" + (seriesAnalysis.content || "").slice(0, 2500)); ``` ### Example Output ```text theme={"dark"} Series: "Marketing Masterclass 2026" — 6 sessions Analyzing S1: "The Landscape: Where Marketing Is Heading" Analyzing S2: "Audience Research That Actually Works" Analyzing S3: "Content Strategy Framework" Analyzing S4: "Paid Media Optimization Deep Dive" Analyzing S5: "Measurement & Attribution" Analyzing S6: "Putting It All Together — Live Workshop" WEBINAR SERIES INTELLIGENCE — "Marketing Masterclass 2026" ================================================================= Session Title Plays Finish% Hook Emotion Clarity ----------------------------------------------------------------- S1 The Landscape: Where Market 2,400 71.2% 82 7.8 88 S2 Audience Research That Actu 1,800 68.5% 75 7.1 91 S3 Content Strategy Framework 1,200 54.3% 61 5.4 74 S4 Paid Media Optimization Dee 840 42.1% 48 4.2 69 S5 Measurement & Attribution 620 38.7% 44 3.8 65 S6 Putting It All Together — 580 61.2% 71 6.9 82 ## Series Engagement Arc ### Peak: Session 1 (71.2% finish rate, hook 82) Strong opening with broad relevance. The "landscape" format gives viewers context without demanding commitment. High emotion (7.8) from future-focused optimism and FOMO triggers. ### Critical Drop: Sessions 3-5 (finish rate drops from 68% to 39%) The series loses 56% of Session 1's audience by Session 5. The pattern: - **Session 3**: Cognitive load spikes (7.2/10) — the framework is too dense for a webinar format. Pacing drops to 4.8/10. Viewers disengage when they can't keep up. - **Session 4**: Hook score 48 — the title "Deep Dive" signals effort, scaring away casual viewers. Emotion drops to 4.2 — all tactical, no story. - **Session 5**: "Measurement" is the hardest topic to make engaging. Clarity 65 suggests the content assumes too much prior knowledge. ### Recovery: Session 6 (61.2% finish rate) The live workshop format re-engages survivors. Interactive format lifts emotion back to 6.9. Viewers who made it to S6 are committed. ### Recommendations for Next Series 1. **Front-load high-emotion sessions** — move the workshop to S3 to catch viewers before they drop 2. **Cap cognitive load at 5.0/10** — Session 3's framework needs to be split into two lighter sessions 3. **Rename Session 4** — "Deep Dive" repels. Try "The 3 Paid Media Wins You Can Implement This Week" (action-oriented, bounded) 4. **Add hooks to every session** — Sessions 4-5 open with slides. Open with a result: "This framework saved one client $240K last quarter" 5. **Mid-series re-engagement email** — After Session 3, send a "catch up in 5 minutes" summary to win back drop-offs ``` ### Error Handling Vimeo uses "albums" (also called showcases) to group videos. The API endpoint is `/me/albums/{id}/videos`. Folders (for organization) use a different endpoint: `/me/folders/{id}/videos`. Ensure you're using the correct one. The `sort=manual` parameter returns videos in the order you arranged them in the showcase. If you want chronological order instead, use `sort=date`. The session numbering in the code follows the API sort order. For long series, batch Video Analysis into groups of 5 with 60-second pauses between groups to respect both Vimeo and Mavera rate limits. The total analysis time scales linearly with session count. *** ## What's Next Back to Vimeo integration overview Score your entire video catalog Full reference for POST /api/v1/video-analysis Full reference for POST /api/v1/mave/chat