What challenges did Guidesly face before AI implementation?

Outdoor guides were spending hours each day updating websites, social channels, and email campaigns. Manual tagging of species, trip details, and SEO content was slow, inconsistent, and diverted time away from guiding clients.

What was the impact of the AI solution?

Content production time dropped from about 13 minutes to about 2 minutes per report. Adoption grew from just over 100 reports in early 2025 to nearly 340 by July 2025, and content output increased from under 800 assets to more than 2,500. Among the five most active guides, average monthly revenue increased from about $3,000 in January 2025 to more than $27,000 in July 2025.

Source

Evidence: Low35/100

Guidesly automated trip-report generation and marketing content using Amazon Bedrock, SageMaker, and Step Functions

Use case typeAI platformUpdated Jun 13, 2026

Guidesly is a vertical SaaS platform for outdoor guides that built Jack AI to turn trip media and metadata into SEO-friendly trip reports and multi-channel marketing content. The system runs as a serverless AWS workflow that enriches media, detects fish species with a hybrid vision pipeline, generates content with Amazon Bedrock, and publishes assets for websites, social posts, and email.

Organization: Guidesly
Industry: Consumer & Food
Location: United States
Published: April 2026

Reported outcomes

27,000 USD

average monthly revenueRevenue & growth

13 minutesreport creation time2 minutesreport creation time100 reportsreports generated340 reportsreports generated800 assetscontent output

Strategic outcomes

New product / capabilityAutomated trip reports and marketing contentSpeed & agilityReduced content production cycleScale & capacityScaled content and report outputCost efficiencyIncreased guide revenue through automation

Why do we believe this?Outcome claims, sources, and evidence checks

Normalized claim

Report creation time: 13 minutes decrease

AWS Machine Learning BlogApr 14, 2026Blog postExplicit claimLow evidence strength

asset generation time dropping from 13 minutes in December 2024 to just two minutes by August 2025

Normalized claim

Report creation time: 2 minutes decrease

AWS Machine Learning BlogApr 14, 2026Blog postExplicit claimLow evidence strength

asset generation time dropping from 13 minutes in December 2024 to just two minutes by August 2025

Normalized claim

Reports generated: 100 reports increase

AWS Machine Learning BlogApr 14, 2026Blog postExplicit claimLow evidence strength

growing from just over 100 reports in early 2025 to nearly 340 reports by July 2025

Normalized claim

Reports generated: 340 reports increase

AWS Machine Learning BlogApr 14, 2026Blog postExplicit claimLow evidence strength

growing from just over 100 reports in early 2025 to nearly 340 reports by July 2025

Normalized claim

Content output: 800 assets increase

AWS Machine Learning BlogApr 14, 2026Blog postExplicit claimLow evidence strength

Content output has scaled dramatically, from under 800 assets in early 2025 to more than 2,500 assets by midsummer

Normalized claim

Content output: 2,500 assets increase

AWS Machine Learning BlogApr 14, 2026Blog postExplicit claimLow evidence strength

Content output has scaled dramatically, from under 800 assets in early 2025 to more than 2,500 assets by midsummer

Normalized claim

Average monthly revenue: 3,000 USD increase

AWS Machine Learning BlogApr 14, 2026Blog postExplicit claimLow evidence strength

Average monthly revenue grew from approximately $3,000 in January 2025 to more than $27,000 by July 2025

Normalized claim

Average monthly revenue: 27,000 USD increase

AWS Machine Learning BlogApr 14, 2026Blog postExplicit claimLow evidence strength

Average monthly revenue grew from approximately $3,000 in January 2025 to more than $27,000 by July 2025

Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks

Customer: Guidesly
Provider: AWS
Maturity: Unknown
Linked source: AWS Machine Learning Blog

No explicit deployment-stage evidence found.

Customer identity supportedSource describes one deploymentMaturity evidence evaluated

Primary read

Use case focus

Showing 3 of 4

1Generative AI content generation
2Marketing automation
3Computer vision

Outdoor guides were spending hours each day updating websites, social channels, and email campaigns.
Manual tagging of species, trip details, and SEO content was slow, inconsistent, and diverted time away from guiding clients.

Guidesly implemented an automated, event-driven pipeline on AWS using Amazon API Gateway, AWS Step Functions, AWS Lambda, Amazon S3, Amazon RDS for PostgreSQL, Amazon SageMaker AI, and Amazon Bedrock AgentCore.
The workflow extracts metadata, enriches trip context, performs computer vision for fish detection, uses prompt-constrained generative AI for tone-aligned trip reports, and produces assets for multiple publishing channels.
Guidesly also uses guide review and auto-publish controls to balance quality control with automation.

Technologies

Amazon Bedrock Amazon Bedrock AgentCore Amazon SageMaker AI AWS Step Functions Amazon API Gateway Amazon S3 Amazon RDS for PostgreSQL AWS Lambda Amazon SNS

Content production time dropped from about 13 minutes to about 2 minutes per report.
Adoption grew from just over 100 reports in early 2025 to nearly 340 by July 2025, and content output increased from under 800 assets to more than 2,500.
Among the five most active guides, average monthly revenue increased from about $3,000 in January 2025 to more than $27,000 in July 2025.

Architecture

A serverless, event-driven workflow starts with trip media uploads through Amazon API Gateway and is orchestrated by AWS Step Functions. The pipeline extracts EXIF and trip metadata, enriches it with weather and water conditions from the same time and location, applies a hybrid computer vision approach using custom-trained models in Amazon SageMaker AI plus multimodal foundation models through Amazon Bedrock, improves media for web delivery, and then uses AWS Lambda functions to generate SEO trip reports, social captions, and email content. Processed artifacts are stored in Amazon S3 and Amazon RDS for downstream reuse. Guides can review outputs or auto-publish them.

Sources & evidence1

Evidence: Low35/100Evidence strength