Form-filling & portal RPA agents
Fill complex government/enterprise web forms with vision+DOM agents when no API exists — retries, selectors, and human-hand-off included.
At a glance — Oct 2026
Updated 2026-10-27 · forward this page: /jtbds/form-filling-rpa#briefScores as of 2026-09-14 (43 days old; Depot marks scores stale after 30 days). The pick is still Depot's current editorial pick; it has not been re-reviewed since. Prices below carry their own dates.
- Depot Pick
- Skyvern · 7.88/10 for this job (curated estimate, high confidence)
Distinct from generic computer-use browsers: form/workflow success rate. Confidence: medium.
- Runner-up
- Anchor Browser · 7.16/10
- When not to use the pick
- Need stealth multi-session browsers without RPA opinionation (Anchor/Browserbase), or open-source self-host Browser Use.
- Lock-in / migration
- The pick has lower stored lock-in risk than runner-up Anchor Browser (4 vs 4.8). Pick exit signals: open source (provider tag `oss`). Self-host fallback listed for this job: Mind2Web.
- Sourced price (no comparable unit)
Pick: no sourced price in this job's unit (no_matching_sourced_price).
No cheapest SKU (no_comparable_unit_for_job). No price was invented.
- Free option
- Mind2Web (oss) — source, as of 2026-10-25
- Failure modes to watch
- Benchmark protocol mismatch: Store assisted-or-not, subset, and harness version beside every cited score. Refuse a ranking that mixes those fields.
- Collateral side effects: Snapshot the workspace or app state, then diff it against an allowlist. A passing check plus an unexpected diff is a failure.
- Confirmation skip: Gate those tool names on an approval id recorded before the call. A missing approval is a failure even if the downstream tool returns success.
- GUI grounding miss: After each GUI action, compare the resulting screen or accessibility tree to the control the plan named. Stop when they differ.
- Partial tool success: Require a per-item status and a failure count. Success for the task requires the failed count to be zero or explicitly handed to a retry queue.
- Prompt injection: Compare each tool call to the original user task. If the call only makes sense given text that arrived from a fetched page, file, or message, stop and ask. Record which source the instruction came from. This catalog does not store payloads or attack steps.
Cite: Agent Provider Depot, Depot Pick for form-filling-rpa: skyvern, scores as of 2026-09-14. Agents: GET /api/decide?jtbd=form-filling-rpa
Free Form-fill RPA options · for computer-use agents
Skyvern
Distinct from generic computer-use browsers: form/workflow success rate. Confidence: medium.
Pricing (directional): As of 2026-09-14 (skyvern.com/pricing): Free 5k credits (1 concurrent); Hobby $29/mo / 30k credits / 10 concurrent; Pro $149/mo / 150k credits / 25 concurrent; Enterprise custom (100 concurrent, HIPAA, SOC2, self-host). A run is one workflo…
Lock-in risk: higher = more lock-in (worse). Overall already inverts this dimension.
Pick for ops/RPA-replacement browser agents (invoices, portals, 2FA). Not a substitute for E2B/Cua desktops. Browser Use Cloud if you want a general NL agent loop instead of workflow runs.
Quote for Form-filling & portal RPA agents
Depot Pick stays Skyvern. Prices below are sourced SKU rows only (as of 2026-10-27). Input and output are not blended. GET /api/quote?jtbd=form-filling-rpa
Nothing was compared. no comparable sourced unit for this job; chat input $/1M and other units were not borrowed pickIsPriceWinner is null.
- Free usd_per_month $0 source as of 2026-10-03
- Hobby usd_per_month $29 source as of 2026-10-03
- Pro usd_per_month $149 source as of 2026-10-03
- Skyvern SMS number usd_per_number_month $10 source as of 2026-10-03
1 of 5 candidates have no sourced price row. 5 are excluded from the Matching price comparison (none). no comparable sourced unit for this job; chat input $/1M and other units were not borrowed
Runners-up
Anchor Browser
Strong when bot-detection and authenticated computer-use matter. A/B vs Browserbase/Kernel.
Browser Use Cloud
Pick when you want an agent-native browser loop, not just a hosted Chromium. Browserbase still wins pure…
Hyperbrowser
Pick when you want hosted OpenAI/Claude computer-use on stealth Chromium without owning the browser fleet…
Browserbase
Depot default for agents that need a real browser. Pair with Stagehand/Browser Use for the reasoning loop.
When NOT to use the top pick
Need stealth multi-session browsers without RPA opinionation (Anchor/Browserbase), or open-source self-host Browser Use.
Full ranking (score table)
Ranked with this JTBD's weights. Scores are curated estimates unless marked otherwise. Agents: prefer /api/decide then this table for tie-breaks.
| # | Provider | Overall | Fit | $/perf | Latency | DX | As of |
|---|---|---|---|---|---|---|---|
| 1 | Browserbase | 8.3 | 9.2 | 7.5 | 8.8 | 9.4 | 2026-10-19 |
| 2 | SkyvernDepot Pick | 7.9 | 8.4 | 8.0 | 7.8 | 8.2 | 2026-09-14 |
| 3 | Hyperbrowser | 7.8 | 8.2 | 8.2 | 7.8 | 8.4 | 2026-09-14 |
| 4 | Browser Use Cloud | 7.4 | 8.0 | 7.8 | 7.0 | 8.4 | 2026-09-14 |
| 5 | Anchor Browser | 7.2 | 7.8 | 7.2 | 7.2 | 8.0 | 2026-09-14 |
Score methodology for this job
Distinct from generic computer-use browsers: form/workflow success rate. Confidence: medium.
capabilityFit: 32%pricePerformance: 12%latencyReliability: 14%developerDx: 12%privacyPosture: 12%lockInRisk: 8%maturity: 10%